© 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. 29917
    Prev
    Next
    INDEX
    Explanations

    not

    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
    اني
    -0.06
    aws
    -0.06
     gentle
    -0.06
    tha
    -0.06
    yd
    -0.06
    عر
    -0.06
     scept
    -0.06
     정부
    -0.06
    ematic
    -0.06
     '('
    -0.06
    POSITIVE LOGITS
     Crist
    0.07
    revolution
    0.07
     hebben
    0.07
     erotisch
    0.07
    sah
    0.06
    isión
    0.06
    .Timeout
    0.06
    득
    0.06
    .stub
    0.06
    (UInt
    0.06
    Activations Density 0.003%

    No Known Activations