© 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. 41421
    Prev
    Next
    INDEX
    Explanations

    OPSIS

    np_max-act · gemini-2.0-flash

    The neuron detects section-heading tokens (e.g. “NAME,” “SYNOPSIS,” “DESCRIPTION”) in man-page–style documents.

    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
    .fun
    -0.06
     gül
    -0.06
    Bed
    -0.06
    _Error
    -0.06
    _UDP
    -0.05
     uzavř
    -0.05
     hàm
    -0.05
    字幕
    -0.05
     poate
    -0.05
     mük
    -0.05
    POSITIVE LOGITS
    esine
    0.08
    فی
    0.07
     reconciliation
    0.07
    conciliation
    0.07
     possible
    0.07
    ottie
    0.07
    nie
    0.07
     Congressional
    0.06
     strengthened
    0.06
     entities
    0.06
    Activations Density 0.002%

    No Known Activations