© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89030
    Prev
    Next
    INDEX
    Explanations

    Question words/articles

    np_max-act · gemini-2.0-flash

    The neuron detects individual action‐item steps or directives in a procedural plan, such as numbered tasks with scheduling and responsibility details.

    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
     Brigade
    -0.07
     Expires
    -0.07
     Pool
    -0.07
    uar
    -0.07
    _CENTER
    -0.06
    Y
    -0.06
     под
    -0.06
    ENGINE
    -0.06
     kiss
    -0.06
    grey
    -0.06
    POSITIVE LOGITS
     README
    0.06
     Matchers
    0.06
    увати
    0.06
     currentState
    0.06
     أغ
    0.06
     nextState
    0.05
     участие
    0.05
    _CNTL
    0.05
     '-')↵
    0.05
     بدن
    0.05
    Activations Density 0.081%

    No Known Activations