© 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. 11-RESID-POST-AA
    11. 93992
    Prev
    Next
    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash

    structure and organization in a programming context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _RESET
    -0.08
    zb
    -0.07
    iterr
    -0.07
    )<<
    -0.07
     Reserve
    -0.07
     घर
    -0.06
    american
    -0.06
    .curr
    -0.06
    Kar
    -0.06
    Π
    -0.06
    POSITIVE LOGITS
    $model
    0.07
    orrow
    0.07
    (commit
    0.07
    认识
    0.06
    ивается
    0.06
    
    0.06
     kontakte
    0.06
    روه
    0.06
     пев
    0.06
    RELATED
    0.06
    Activations Density 0.010%

    No Known Activations