© 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. 73299
    Prev
    Next
    INDEX
    Explanations

    electronics/manufacturing

    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
     kvinna
    -0.07
    örü
    -0.06
    Unix
    -0.06
     MIME
    -0.06
    (Field
    -0.06
     Nope
    -0.06
     Gentle
    -0.06
     beats
    -0.06
    .WriteByte
    -0.06
     tarea
    -0.06
    POSITIVE LOGITS
    _af
    0.07
     문화
    0.06
     Nes
    0.06
    CCI
    0.06
    _MED
    0.06
     Bran
    0.06
    worth
    0.06
    मत
    0.06
    -trained
    0.06
    InternalServerError
    0.06
    Activations Density 0.243%

    No Known Activations