© 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. 109391
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects floating‐point numeric tokens (probability weights) in the probability problem formulas.

    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
    ?>">↵
    -0.06
    _DEL
    -0.06
    .buffer
    -0.06
    ीक
    -0.06
     suchen
    -0.06
    raya
    -0.06
     tm
    -0.06
    нє
    -0.06
    .getHeader
    -0.06
    Ģ
    -0.06
    POSITIVE LOGITS
     Crypto
    0.07
    редел
    0.06
     sprung
    0.06
     jorn
    0.06
     Mass
    0.06
    IDENT
    0.06
    -.
    0.06
    -section
    0.06
     ej
    0.06
    Environmental
    0.06
    Activations Density 0.003%

    No Known Activations