Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 83578
    Prev
    Next
    INDEX
    Explanations

    football

    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
    лась
    -0.07
    .User
    -0.06
    .st
    -0.06
     fortified
    -0.06
    chluss
    -0.06
     segue
    -0.06
    /module
    -0.06
    Apart
    -0.06
    Viewer
    -0.06
    @Getter
    -0.06
    POSITIVE LOGITS
    OPY
    0.07
    'value
    0.06
    OUCH
    0.06
    件事
    0.06
    反
    0.06
     Capture
    0.06
     bum
    0.06
     Christine
    0.06
     wandering
    0.06
     contributions
    0.06
    Activations Density 0.008%

    No Known Activations