© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8763
    Prev
    Next
    INDEX
    Explanations

    reports, data, research

    np_max-act · gemini-2.0-flash

    The neuron responds to words that signal reported or second-hand information—i.e. attribution hedges like “reports,” “indicates,” “accounts,” “suggest,” “independent,” 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
    3
    -0.06
     sunset
    -0.06
    rary
    -0.06
    ้ก
    -0.06
     поэтому
    -0.06
     FOX
    -0.06
     Sharon
    -0.06
     archives
    -0.06
    Roger
    -0.06
    body
    -0.06
    POSITIVE LOGITS
    .SH
    0.07
    createQueryBuilder
    0.07
    گاه
    0.07
     councill
    0.06
    .fd
    0.06
     adel
    0.06
    dT
    0.06
    ię
    0.06
    aic
    0.06
    _IDENTIFIER
    0.06
    Activations Density 0.038%

    No Known Activations