© 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. 15-RESID-POST-AA
    11. 9842
    Prev
    Next
    INDEX
    Explanations

    })(

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complexes
    -0.07
    inscription
    -0.06
     entsprech
    -0.06
    lesen
    -0.06
    senha
    -0.06
    LEY
    -0.06
     getInput
    -0.06
     Tail
    -0.06
     симптом
    -0.06
    ックス
    -0.06
    POSITIVE LOGITS
    .run
    0.06
    rypt
    0.06
     PORT
    0.06
     validate
    0.06
    ange
    0.06
    गढ
    0.06
     shut
    0.06
     Ay
    0.06
     kur
    0.06
    /editor
    0.06
    Activations Density 0.009%

    No Known Activations