© 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. 128796
    Prev
    Next
    INDEX
    Explanations

    video games

    np_max-act · gemini-2.0-flash

    text related to video game mechanics and features.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on in‐game proper names and key game‐specific terms (e.g. “Chao,” “Dreamcast,” “Hero Chao,” “Dark Chao,” etc.).

    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
    eno
    -0.07
    ilyn
    -0.07
     ش
    -0.06
     regulator
    -0.06
    Primitive
    -0.06
     Bench
    -0.06
    ?f
    -0.06
     QStringLiteral
    -0.06
    “That
    -0.06
    shiv
    -0.06
    POSITIVE LOGITS
     запас
    0.06
    .icons
    0.06
     ورز
    0.06
     Luc
    0.06
     summon
    0.06
     Warn
    0.06
     spouses
    0.06
    ologic
    0.06
     Obst
    0.06
     výzkum
    0.06
    Activations Density 0.036%

    No Known Activations