© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 127186
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    This neuron detects authorial claim or stance phrases—verbs like “propose,” “argue,” or “suggest” that introduce the paper’s central hypotheses or arguments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    clause-introducing markers in academic prose that link reporting verbs or assertions to their subordinate content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ebin
    -0.07
     докум
    -0.06
    .getMethod
    -0.06
    Samples
    -0.06
    height
    -0.06
    ُّ
    -0.06
     челов
    -0.06
     campuses
    -0.06
    -MM
    -0.06
     defamation
    -0.06
    POSITIVE LOGITS
    olleyError
    0.07
    rade
    0.06
     sapi
    0.06
     teaspoon
    0.06
     Initialize
    0.06
     Trit
    0.06
    .BooleanField
    0.06
    CHA
    0.06
    친
    0.06
    ี้↵
    0.06
    Activations Density 0.060%

    No Known Activations