© 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. 43340
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash

    The neuron reliably fires on occurrences of the word “None,” marking sections or fields where no content or errors are reported.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    requests for structured output or information.

    oai_token-act-pair · gpt-4o-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
    \CMS
    -0.06
    configuration
    -0.06
     Technologies
    -0.06
     unloaded
    -0.06
    발
    -0.06
     shark
    -0.06
     slew
    -0.06
     photograph
    -0.06
     prosecutor
    -0.06
     ıs
    -0.06
    POSITIVE LOGITS
    Mutable
    0.07
    jejer
    0.07
    .ImageAlign
    0.06
    _OLD
    0.06
    版
    0.06
    uy�
    0.06
     Costume
    0.06
    gif
    0.06
    NotificationCenter
    0.06
    *(-
    0.06
    Activations Density 0.062%

    No Known Activations