© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 52363
    Prev
    Next
    INDEX
    Explanations

    jurisdiction

    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
     snow
    -0.07
     salaries
    -0.07
     Moving
    -0.07
     swear
    -0.07
    hydrate
    -0.07
    StackTrace
    -0.06
     Bars
    -0.06
    avy
    -0.06
    復
    -0.06
    Encode
    -0.06
    POSITIVE LOGITS
    Unmarshaller
    0.06
     sentir
    0.06
    'field
    0.06
     Wonderful
    0.06
     thơm
    0.06
     ►
    0.06
    .Usuario
    0.06
     інші
    0.06
    ��
    0.06
    SHOT
    0.06
    Activations Density 0.006%

    No Known Activations