© 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. 7-RESID-POST-AA
    11. 115588
    Prev
    Next
    INDEX
    Explanations

    Story/Prompt beginnings

    np_max-act · gemini-2.0-flash

    user-posed questions, especially interrogative sentences (yes/no or wh- questions) within the dialogue context.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quis
    -0.07
    عدد
    -0.07
    MAP
    -0.07
    xDA
    -0.06
     ench
    -0.06
    QUEUE
    -0.06
    -On
    -0.06
    owan
    -0.06
    }:${
    -0.06
     insult
    -0.06
    POSITIVE LOGITS
    _trial
    0.07
    Amy
    0.06
    .response
    0.06
    _EXPR
    0.06
     onclick
    0.06
    paredStatement
    0.06
    tok
    0.06
    Broad
    0.06
     žid
    0.06
    Remaining
    0.05
    Activations Density 0.152%

    No Known Activations