© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44200
    Prev
    Next
    INDEX
    Explanations

    technology and science

    np_max-act · gemini-2.0-flash

    This neuron activates on specialized technical or scientific terms (e.g. domain-specific nouns like “lung,” “neural,” “language,” “model,” 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
    .Create
    -0.07
    -only
    -0.07
     cosmic
    -0.07
    plant
    -0.06
    expected
    -0.06
    -notch
    -0.06
     Realm
    -0.06
    _menus
    -0.06
    .is
    -0.06
    ometry
    -0.06
    POSITIVE LOGITS
     ham
    0.07
    BinContent
    0.06
    уча
    0.06
    'r
    0.06
    ！」↵↵
    0.06
     )↵↵↵
    0.06
     şeklinde
    0.06
    ivityManager
    0.06
    istributed
    0.06
    ?>↵↵↵
    0.06
    Activations Density 0.333%

    No Known Activations