© 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. 44396
    Prev
    Next
    INDEX
    Explanations

    patent applications

    np_max-act · gemini-2.0-flash

    The neuron fires weakly on punctuation (commas and periods) and common function words (e.g. conjunctions, articles, and short grammatical markers) that mark phrase or clause boundaries.

    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
     coder
    -0.07
     حاضر
    -0.06
    _vis
    -0.06
    (meta
    -0.06
     Romans
    -0.06
    typing
    -0.06
    елефон
    -0.06
    _leader
    -0.06
     inviting
    -0.06
     registrazione
    -0.06
    POSITIVE LOGITS
    KNOWN
    0.06
     المل
    0.06
     justice
    0.06
    ские
    0.06
     Colts
    0.06
     Walls
    0.06
     canoe
    0.06
    getColumn
    0.06
    wp
    0.06
     Jub
    0.06
    Activations Density 0.155%

    No Known Activations