© 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. 23-RESID-POST-AA
    11. 8177
    Prev
    Next
    INDEX
    Explanations

    Arabic character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     familiar
    -0.07
    esin
    -0.06
    softmax
    -0.06
    мотреть
    -0.06
     спас
    -0.06
     görüş
    -0.06
    GetSize
    -0.06
    shift
    -0.06
    975
    -0.06
    633
    -0.06
    POSITIVE LOGITS
     řadu
    0.07
    OLD
    0.07
    응
    0.07
    (del
    0.07
     непри
    0.06
     phức
    0.06
    薬
    0.06
    **,
    0.06
     인천
    0.06
     xpath
    0.06
    Activations Density 0.005%

    No Known Activations