© 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. 89669
    Prev
    Next
    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash

    The neuron detects imperative, advice-giving phrases—i.e. command sentences telling you what to do (or not to do).

    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
     Pazar
    -0.07
    -await
    -0.06
    found
    -0.06
    Paginator
    -0.06
    (background
    -0.06
     vaše
    -0.06
     boredom
    -0.06
    avec
    -0.06
    puter
    -0.06
    -events
    -0.06
    POSITIVE LOGITS
    ☆
    0.06
     меж
    0.06
    hold
    0.06
    。”
    0.06
    ;↵
    0.06
    Impro
    0.06
     dress
    0.06
    valor
    0.06
    лого
    0.06
    gili
    0.06
    Activations Density 0.044%

    No Known Activations