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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130235
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numbers (decimal fractions) in the 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
    _surf
    -0.08
    	nil
    -0.06
    _bloc
    -0.06
     Gerald
    -0.06
     Enumerator
    -0.06
    .emptyList
    -0.06
    Severity
    -0.06
    -Bold
    -0.06
     πραγμα
    -0.06
    Probe
    -0.06
    POSITIVE LOGITS
    genic
    0.07
     gratuitement
    0.07
     operations
    0.07
    詩
    0.07
     EXPORT
    0.07
    GING
    0.06
     abol
    0.06
    inations
    0.06
    zę
    0.06
     boiler
    0.06
    Activations Density 0.209%

    No Known Activations