© 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. 113982
    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
    098
    -0.07
    씨
    -0.07
     sym
    -0.06
     thù
    -0.06
    ListGroup
    -0.06
    178
    -0.06
     juga
    -0.06
     overweight
    -0.06
     olup
    -0.06
    788
    -0.06
    POSITIVE LOGITS
    에도
    0.06
    eded
    0.06
    ITER
    0.06
     hanno
    0.06
     clearInterval
    0.06
    BAL
    0.06
    uner
    0.06
    Anchor
    0.05
    ник
    0.05
     основных
    0.05
    Activations Density 0.042%

    No Known Activations