© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47109
    Prev
    Next
    INDEX
    Explanations

    ault

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens from hyphenated sports-news URL slugs—especially the “chiefs-hire-chris-ault-as-consultant” path on profootballtalk.nbcsports.com.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    the brand and model specifications of printers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isory
    -0.06
    opal
    -0.06
    ené
    -0.06
    Pay
    -0.06
    /state
    -0.06
    zdy
    -0.06
                ↵            ↵
    -0.06
    ↵↵↵↵↵↵↵↵↵
    -0.06
     bakış
    -0.05
     //////////////////////////////////////////////////////////////////////
    -0.05
    POSITIVE LOGITS
    igh
    0.07
    Tank
    0.07
    documentation
    0.07
     seks
    0.06
    outside
    0.06
    LER
    0.06
    "x
    0.06
    жа
    0.06
    ighet
    0.06
    .fade
    0.06
    Activations Density 0.985%

    No Known Activations