Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 129414
    Prev
    Next
    INDEX
    Explanations

    cricket

    np_max-act · gemini-2.0-flash

    The neuron is picking out numeric tokens (scores, years, and other statistics) in the cricket-related text.

    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
    clamation
    -0.07
    etty
    -0.06
    ogenous
    -0.06
    TOKEN
    -0.06
    udence
    -0.06
    .TextView
    -0.06
     Feng
    -0.06
    ẹ
    -0.06
    syscall
    -0.06
    062
    -0.06
    POSITIVE LOGITS
    Door
    0.07
     Enumerator
    0.06
     sơn
    0.06
     Lotus
    0.06
    Mailer
    0.06
     kicks
    0.06
    .mozilla
    0.06
    .labelX
    0.06
    _LIST
    0.06
    ParseException
    0.06
    Activations Density 0.010%

    No Known Activations