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. 122285
    Prev
    Next
    INDEX
    Explanations

    newline

    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
     实
    -0.06
     advertisements
    -0.06
    umor
    -0.06
    ioxide
    -0.06
    STER
    -0.06
    abies
    -0.06
     представляет
    -0.06
    -space
    -0.06
    -caption
    -0.06
    ิป
    -0.06
    POSITIVE LOGITS
    だった
    0.07
    Purple
    0.07
    /library
    0.06
    (Set
    0.06
    .setText
    0.06
    871
    0.06
    咲
    0.06
     jylland
    0.06
    _TABLE
    0.06
    \_
    0.06
    Activations Density 0.084%

    No Known Activations