© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 35679
    Prev
    Next
    INDEX
    Explanations

    final

    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
     cunning
    -0.06
    formData
    -0.06
     Mass
    -0.06
    ului
    -0.06
    equal
    -0.06
    Specify
    -0.06
     coinc
    -0.06
    力
    -0.06
     براى
    -0.05
     passé
    -0.05
    POSITIVE LOGITS
    SSION
    0.07
     일
    0.07
    //================================================
    0.07
    FIG
    0.07
    ничес
    0.07
     इनक
    0.07
     alignItems
    0.06
     NST
    0.06
     أث
    0.06
     Dys
    0.06
    Activations Density 0.009%

    No Known Activations