© 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. 29998
    Prev
    Next
    INDEX
    Explanations

    Publications

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens (e.g. volume, page, year, or figure numbers in citations).

    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
     AD
    -0.07
    -slot
    -0.06
    ngth
    -0.06
     ACTIVE
    -0.06
     bombers
    -0.06
    اسی
    -0.06
    ared
    -0.06
    _Create
    -0.06
     Lynn
    -0.06
     Question
    -0.06
    POSITIVE LOGITS
     eoqkrvldkf
    0.07
    188
    0.06
    86
    0.06
    �
    0.06
     sito
    0.06
    weed
    0.06
    50
    0.06
     totiž
    0.06
    "s
    0.06
     demol
    0.06
    Activations Density 0.003%

    No Known Activations