© 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. 92441
    Prev
    Next
    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash

    The neuron fires on programming identifiers that look like library, framework, or namespace names (e.g. capitalized or project‐specific tokens).

    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
    als
    -0.07
    _community
    -0.07
    .each
    -0.07
     whoever
    -0.07
    matches
    -0.06
    iento
    -0.06
    (dec
    -0.06
    users
    -0.06
    teams
    -0.06
    endl
    -0.06
    POSITIVE LOGITS
    .setIcon
    0.07
     rolls
    0.07
     фев
    0.06
    伯
    0.06
     date
    0.06
     kaliteli
    0.06
    <State
    0.06
     semiclass
    0.06
    :[↵
    0.06
     marched
    0.06
    Activations Density 0.028%

    No Known Activations