© 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. 91737
    Prev
    Next
    INDEX
    Explanations

    Video games

    np_max-act · gemini-2.0-flash

    This neuron fires on words and phrases that describe progressing through or completing a game (e.g. finishing, journey, through, course, progress, missions).

    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
    AnimationFrame
    -0.07
    USERNAME
    -0.07
     Chemistry
    -0.07
     chemistry
    -0.07
    	os
    -0.07
     SPACE
    -0.07
     {"
    -0.07
     pharmacy
    -0.07
     tuz
    -0.07
     Kelley
    -0.06
    POSITIVE LOGITS
     جنسی
    0.07
    _ALLOWED
    0.07
    _groups
    0.06
     profesyonel
    0.06
    $page
    0.06
    Specific
    0.06
     creampie
    0.06
     Vault
    0.06
    푸
    0.06
     căn
    0.05
    Activations Density 0.024%

    No Known Activations