© 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 EvalsExportsAPI 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. 56705
    Prev
    Next
    INDEX
    Explanations

    Increase

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs and terms that denote positive modulation (increasing, stimulating, enhancing) of biological processes or levels.

    oai_token-act-pair · o4-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
    unprocessable
    -0.07
    /chat
    -0.07
    Correct
    -0.07
    .ix
    -0.07
    utowired
    -0.06
    orld
    -0.06
     associate
    -0.06
     post
    -0.06
    ICLE
    -0.06
     useState
    -0.06
    POSITIVE LOGITS
    eştir
    0.07
    /wiki
    0.07
     Baltimore
    0.06
     jardin
    0.06
    ριά
    0.06
    	env
    0.06
     上涨
    0.06
     Portug
    0.06
    pty
    0.06
    beth
    0.06
    Activations Density 0.027%

    No Known Activations