© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 99607
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    _ary
    -0.07
    _slope
    -0.07
     곧
    -0.06
     Rank
    -0.06
     hwnd
    -0.06
     Manuals
    -0.06
     Ike
    -0.06
    .Live
    -0.06
    _AdjustorThunk
    -0.06
    <|end_header_id|>
    -0.06
    POSITIVE LOGITS
    (setting
    0.07
     NETWORK
    0.07
    _exact
    0.07
    -tech
    0.06
    ursed
    0.06
    .j
    0.06
    .socket
    0.06
    不知道
    0.06
    」，
    0.06
    GR
    0.06
    Activations Density 0.020%

    No Known Activations