© 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
    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. 29394
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
     Nun
    -0.07
     Coff
    -0.06
     #
    -0.06
    NAS
    -0.06
     Sorting
    -0.06
     irresponsible
    -0.06
    (tweet
    -0.06
     condemnation
    -0.06
     sheer
    -0.06
     hứ
    -0.06
    POSITIVE LOGITS
    ulating
    0.07
    (Frame
    0.06
    _at
    0.06
    _active
    0.06
     lékař
    0.06
    /Test
    0.06
    .ScrollBars
    0.06
     prize
    0.06
    (Transaction
    0.06
    .strip
    0.06
    Activations Density 0.000%

    No Known Activations