© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 112036
    Prev
    Next
    INDEX
    Explanations

    to

    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
     yields
    -0.07
     baking
    -0.06
     book
    -0.06
     доход
    -0.06
     만족
    -0.06
     dataframe
    -0.06
    .Fail
    -0.06
     accounted
    -0.06
    fly
    -0.06
     onload
    -0.06
    POSITIVE LOGITS
    \S
    0.07
    utivo
    0.07
     mỹ
    0.06
     pago
    0.06
    ское
    0.06
    054
    0.06
    +-+-+-+-+-+-+-+-
    0.06
    cox
    0.06
    είου
    0.06
    andır
    0.06
    Activations Density 0.022%

    No Known Activations