© 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
    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. 129852
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron detects the phrase “not categorized by position” in category or metadata lines.

    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
    ContentLoaded
    -0.06
     miner
    -0.06
    (Task
    -0.06
     refinery
    -0.06
     migrationBuilder
    -0.06
     Melanie
    -0.06
     arsen
    -0.06
    nout
    -0.06
    "])↵
    -0.06
     cavern
    -0.06
    POSITIVE LOGITS
    difference
    0.07
     passing
    0.07
     locals
    0.07
    struk
    0.07
     STORAGE
    0.07
    wechat
    0.07
    σμός
    0.06
    过程
    0.06
    ,error
    0.06
    Declaration
    0.06
    Activations Density 0.004%

    No Known Activations