© 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. 109222
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical programming/code content and syntax, especially C/Java-style code and developer-oriented prompts or metadata.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    iaux
    -0.07
     revert
    -0.07
    rounded
    -0.07
     daunting
    -0.06
    .Clone
    -0.06
    .sort
    -0.06
    (Auth
    -0.06
    افية
    -0.06
    放在
    -0.06
    lover
    -0.06
    POSITIVE LOGITS
    down
    0.06
    тим
    0.06
    िट
    0.06
     Queens
    0.06
     крит
    0.06
    asset
    0.06
    tol
    0.06
     Credits
    0.06
    üş
    0.06
    či
    0.06
    Activations Density 0.781%

    No Known Activations