© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42768
    Prev
    Next
    INDEX
    Explanations

    el

    np_max-act · gemini-2.0-flash

    This neuron responds to non‐English or otherwise “foreign” tokens—sequences of characters (often with accents or Cyrillic letters) that indicate the text is in a language other than standard English.

    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
     regarded
    -0.07
    _follow
    -0.07
     Argentine
    -0.06
    rd
    -0.06
     cached
    -0.06
     hinted
    -0.06
    slaught
    -0.06
    contre
    -0.06
    618
    -0.06
    Sets
    -0.06
    POSITIVE LOGITS
    proto
    0.07
    ANTA
    0.06
    _Text
    0.06
    紙
    0.06
    ULL
    0.06
    ayscale
    0.06
    (func
    0.06
    eresa
    0.06
     orgy
    0.06
    ocz
    0.06
    Activations Density 0.049%

    No Known Activations