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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 118408
    Prev
    Next
    INDEX
    Explanations

    on

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.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
    reland
    -0.07
    xx
    -0.06
     gb
    -0.06
     Rox
    -0.06
    RX
    -0.06
    underline
    -0.06
    _context
    -0.06
     -------------------------------------------------------------------------
    -0.06
    .”↵↵↵↵
    -0.06
    POSITIVE LOGITS
     taxonomy
    0.07
    ška
    0.06
    有效
    0.06
    opus
    0.06
    onomies
    0.06
    Shown
    0.06
     Chelsea
    0.06
    RESH
    0.06
    렬
    0.06
    .toJSON
    0.06
    Activations Density 0.018%

    No Known Activations