© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109234
    Prev
    Next
    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash

    The neuron activates on command‐line invocation phrases—e.g. “pip install,” “running the following command,” or tool‐invocation tokens—i.e. terminal commands in instructions.

    oai_token-act-pair · o4-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
     đẩy
    -0.07
    ющего
    -0.06
    juan
    -0.06
     शर
    -0.06
    Areas
    -0.06
     ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄
    -0.06
    esda
    -0.06
     casinos
    -0.06
    edeyse
    -0.06
     Chern
    -0.06
    POSITIVE LOGITS
     pundits
    0.07
    itioner
    0.07
    fit
    0.06
    ネット
    0.06
    ृष
    0.06
    sequ
    0.06
    _SESSION
    0.06
     pacing
    0.06
    )(↵
    0.06
    (bitmap
    0.06
    Activations Density 0.016%

    No Known Activations