© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125248
    Prev
    Next
    INDEX
    Explanations

    -person

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of game camera viewpoints, especially the tokens “first-person” (and related perspective terms like “isometric”).

    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
     Liebe
    -0.07
     playoffs
    -0.07
    pring
    -0.07
    ecure
    -0.07
     bible
    -0.06
    _duplicate
    -0.06
     conse
    -0.06
    opez
    -0.06
    .magnitude
    -0.06
    abela
    -0.06
    POSITIVE LOGITS
    taxonomy
    0.07
     satisfying
    0.06
     sendo
    0.06
     SER
    0.06
    @media
    0.06
     Decrypt
    0.06
    $fields
    0.06
     получ
    0.06
    ()=>
    0.06
    express
    0.06
    Activations Density 0.002%

    No Known Activations