© 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. 92000
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    This neuron detects phrases offering or suggesting actions, especially “you can” constructions.

    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
     μό
    -0.06
    KO
    -0.06
     olması
    -0.06
     sơn
    -0.06
    195
    -0.06
     touchdowns
    -0.06
     stunt
    -0.06
    ilih
    -0.06
    rol
    -0.06
    RESET
    -0.06
    POSITIVE LOGITS
     тя
    0.07
     pup
    0.06
     pessoa
    0.06
     occasionally
    0.06
     fian
    0.06
     Influ
    0.06
    今日
    0.06
    チーム
    0.06
    صول
    0.06
     champ
    0.06
    Activations Density 0.025%

    No Known Activations