© 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. 38798
    Prev
    Next
    INDEX
    Explanations

    random snippets of text

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on evaluative or descriptive content words—especially adjectives and adverbs used in reviews or promotional language.

    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
     cyclic
    -0.07
    Asset
    -0.06
     your
    -0.06
    -mounted
    -0.06
     Office
    -0.06
     Gaussian
    -0.06
     connectivity
    -0.06
    Modification
    -0.06
     Presence
    -0.06
    Marvel
    -0.06
    POSITIVE LOGITS
    μεν
    0.07
    ์ได
    0.06
     mohlo
    0.06
    .AUTO
    0.06
     멀
    0.06
    .restart
    0.06
     ومع
    0.06
     underworld
    0.06
     ได
    0.06
     mav
    0.06
    Activations Density 0.149%

    No Known Activations