© 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. 43380
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    The neuron fires on prominent single-word headings or keywords in scientific paper titles—typically nouns or gerunds that denote core study components (e.g. “pathophysiology,” “developmental,” “formation,” “structure,” “screening,” “presence”).

    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
    .relationship
    -0.06
     '>
    -0.06
    alnız
    -0.06
    createdAt
    -0.06
     uncompressed
    -0.06
    _uploaded
    -0.06
    >You
    -0.06
    _random
    -0.06
     bán
    -0.06
     Redux
    -0.06
    POSITIVE LOGITS
    udder
    0.07
    번호
    0.06
     после
    0.06
     gobierno
    0.06
     instrumentation
    0.06
    中に
    0.06
    ramento
    0.06
     Bonus
    0.06
    Handles
    0.06
    Welcome
    0.06
    Activations Density 0.044%

    No Known Activations