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. 15-RESID-POST-AA
    6. 122187
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.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
     concession
    -0.07
     concussion
    -0.07
    주는
    -0.06
     descendants
    -0.06
     vulgar
    -0.06
     parms
    -0.06
    -that
    -0.06
    WITHOUT
    -0.06
    /Typography
    -0.06
    POSITIVE LOGITS
     sextreffen
    0.07
    antal
    0.07
    _TS
    0.07
    %</
    0.06
     пес
    0.06
     Endpoint
    0.06
     ẩm
    0.06
     návr
    0.06
    tent
    0.06
    ağ
    0.06
    Activations Density 0.000%

    No Known Activations