© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73807
    Prev
    Next
    INDEX
    Explanations

    Science/technical writing

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on technical/scientific nouns—especially multi-syllable words ending in “-ion” or “-ation” (e.g., “functionalization,” “polymerization,” “voltage”).

    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
    IntegerField
    -0.07
     Interior
    -0.06
    /signup
    -0.06
    WEEN
    -0.06
     intellectual
    -0.06
    -0.06
     đại
    -0.06
    _ROW
    -0.06
    ificar
    -0.06
    Passed
    -0.06
    POSITIVE LOGITS
     binds
    0.06
    Coming
    0.06
     impulses
    0.06
    没有
    0.06
    лаг
    0.06
    .squeeze
    0.06
    ὲ
    0.06
    .Strings
    0.06
    .Raise
    0.05
    rias
    0.05
    Activations Density 0.336%

    No Known Activations