© 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. 125007
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers/privacy policies

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially decimal numbers and other multi‐digit or fractional numeric expressions.

    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
     tut
    -0.06
    rello
    -0.06
     ｰ
    -0.06
    +(\
    -0.06
    Thirty
    -0.06
     cylindrical
    -0.06
    北市
    -0.06
    ircles
    -0.06
    Ti
    -0.06
     Balance
    -0.06
    POSITIVE LOGITS
    :');↵
    0.07
     zru
    0.07
     Functions
    0.06
    Receiver
    0.06
     CNS
    0.06
    servername
    0.06
    "?↵↵
    0.06
    ?
↵
    0.06
    trieve
    0.06
    ($__
    0.06
    Activations Density 0.039%

    No Known Activations