© 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. 68789
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash

    This neuron fires on longer, specialized technical terms (e.g. “invertible,” “foreign,” “constraint,” “parse,” etc.).

    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
    cassert
    -0.06
    Construct
    -0.06
     cure
    -0.06
    /Core
    -0.06
    ({"
    -0.06
     Jinping
    -0.06
     Louis
    -0.06
    _CONT
    -0.06
     lowered
    -0.06
    튜
    -0.06
    POSITIVE LOGITS
     bàn
    0.07
     launder
    0.06
    angent
    0.06
     diagon
    0.06
     تاب
    0.06
     charged
    0.06
    ês
    0.06
     lain
    0.06
    acing
    0.06
     nearer
    0.06
    Activations Density 0.486%

    No Known Activations