© 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. 101706
    Prev
    Next
    INDEX
    Explanations

    Casual questions/responses

    np_max-act · gemini-2.0-flash

    spots questions—tokens that occur in interrogative sentences (question words and the '?' punctuation).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     pleasantly
    -0.07
    .over
    -0.06
     relate
    -0.06
    aines
    -0.06
     demonstrate
    -0.06
    역시
    -0.06
    736
    -0.06
    _z
    -0.06
    [];↵↵
    -0.06
     розповід
    -0.06
    POSITIVE LOGITS
     GObject
    0.07
     história
    0.07
     Chennai
    0.07
     مقر
    0.07
     suất
    0.06
    .Async
    0.06
     Рез
    0.06
     뿐
    0.06
     accountable
    0.06
     asteroid
    0.06
    Activations Density 0.170%

    No Known Activations