© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55476
    Prev
    Next
    INDEX
    Explanations

    Note

    np_max-act · gemini-2.0-flash

    This neuron detects tokens that are part of smartphone model names (e.g., “Note,” “Edge,” “mi,” “Pro,” and associated version numbers).

    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
     BIN
    -0.07
    =Integer
    -0.06
     verge
    -0.06
    =in
    -0.06
    SEG
    -0.06
    核心
    -0.06
    _WORDS
    -0.06
     forfeiture
    -0.06
     حساب
    -0.06
     worst
    -0.06
    POSITIVE LOGITS
    ulf
    0.07
    itably
    0.06
     офі
    0.06
     등을
    0.06
    ेज
    0.06
    '.↵
    0.06
    .first
    0.06
    _padding
    0.06
    _goods
    0.06
    byte
    0.06
    Activations Density 0.009%

    No Known Activations