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. 3-RESID-POST-AA
    6. 122630
    Prev
    Next
    INDEX
    Explanations

    head

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ozí
    -0.07
    :";
    ↵
    -0.06
    .lv
    -0.06
    cery
    -0.06
     pilgrimage
    -0.06
    -relative
    -0.06
     ();
    ↵
    -0.06
    _TestCase
    -0.06
    .ReadAsStringAsync
    -0.06
    icester
    -0.06
    POSITIVE LOGITS
     Administrative
    0.07
     Buildings
    0.06
     boosted
    0.06
    чески
    0.06
     Decide
    0.06
    ề
    0.06
    ongoose
    0.06
    afür
    0.06
    veyor
    0.06
     savoir
    0.06
    Activations Density 0.022%

    No Known Activations