© 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. 13523
    Prev
    Next
    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on snake_case identifiers—tokens containing underscores (e.g. field or parameter names with “_” in them).

    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
    RSS
    -0.06
    nect
    -0.06
    ้าท
    -0.06
    dense
    -0.06
    _DYNAMIC
    -0.06
     erfolgreich
    -0.06
    ,eg
    -0.06
     نس
    -0.06
    ouchers
    -0.06
    JNI
    -0.06
    POSITIVE LOGITS
    شاء
    0.07
     bench
    0.07
     Ab
    0.07
     Der
    0.06
     Cruise
    0.06
     gang
    0.06
    TagName
    0.06
    [m
    0.06
     غر
    0.06
     삼
    0.06
    Activations Density 0.005%

    No Known Activations