© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68774
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens and number‐related strings (e.g. integer and floating‐point values).

    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
    �
    -0.06
    英文
    -0.06
    Vin
    -0.06
    něl
    -0.06
    Budget
    -0.06
    aa
    -0.06
    EmailAddress
    -0.06
    사
    -0.06
    ."↵↵↵↵
    -0.06
     ripe
    -0.06
    POSITIVE LOGITS
    .is
    0.08
     konkrét
    0.07
    .system
    0.07
     Brace
    0.06
    >This
    0.06
    ("<
    0.06
    -option
    0.06
    .getDeclared
    0.06
    (statearr
    0.06
     marshaller
    0.06
    Activations Density 0.167%

    No Known Activations