© 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. 91657
    Prev
    Next
    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of “world” (or related global‐scope terms like “worldwide” or “all around the world”).

    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
     подт
    -0.07
    ibar
    -0.07
    _number
    -0.06
     Idol
    -0.06
    Ý
    -0.06
     Mutual
    -0.06
    .Total
    -0.06
    탈
    -0.06
    _ob
    -0.06
    callback
    -0.06
    POSITIVE LOGITS
     نفسه
    0.07
    _COMPLETED
    0.06
    (push
    0.06
     surname
    0.06
    .endsWith
    0.06
    、↵↵
    0.06
    [class
    0.06
    Pos
    0.06
     nuestras
    0.06
     mound
    0.06
    Activations Density 0.022%

    No Known Activations