© 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. 91584
    Prev
    Next
    INDEX
    Explanations

    biology studies

    np_max-act · gemini-2.0-flash

    This neuron fires on key biological or ecological concept words (e.g. “systems,” “reproduction,” “parental care,” “dispersal,” “mating system,” “life‐history”) that mark important processes or topics.

    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
    _description
    -0.07
     criticized
    -0.07
    ülük
    -0.06
    /bind
    -0.06
     magnificent
    -0.06
     Thanks
    -0.06
     evaluations
    -0.06
     futuro
    -0.06
    MainThread
    -0.06
     webView
    -0.06
    POSITIVE LOGITS
    [List
    0.07
     condos
    0.06
    」
    0.06
    (Image
    0.06
     Immutable
    0.06
     паль
    0.06
     secrets
    0.06
     अपन
    0.06
    伤
    0.06
    dimension
    0.06
    Activations Density 0.013%

    No Known Activations