Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 129142
    Prev
    Next
    INDEX
    Explanations

    salt

    np_max-act · gemini-2.0-flash
    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
    ();?>
    -0.07
     frem
    -0.07
    chor
    -0.07
     adrenaline
    -0.06
    ision
    -0.06
    .IntPtr
    -0.06
    dech
    -0.06
    _COMMENT
    -0.06
     زي
    -0.06
    าษ
    -0.06
    POSITIVE LOGITS
     salts
    0.10
    색
    0.07
    中央
    0.07
    ils
    0.07
    /car
    0.06
     Mah
    0.06
    (all
    0.06
     hi
    0.06
    mark
    0.06
    San
    0.06
    Activations Density 0.003%

    No Known Activations