© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12737
    Prev
    Next
    INDEX
    Explanations

    Grammar and usage

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens that are numeric literals (decimal numbers), effectively detecting floating-point number strings 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
     losses
    -0.06
    ICC
    -0.06
    Persist
    -0.06
    Ptr
    -0.06
     Elite
    -0.06
     stimulated
    -0.06
     Millionen
    -0.06
     حق
    -0.06
     refining
    -0.06
    αρίου
    -0.06
    POSITIVE LOGITS
     погод
    0.07
     tokenId
    0.07
    )findViewById
    0.07
    olkata
    0.07
     PEM
    0.06
    浜
    0.06
     कह
    0.06
     نرم
    0.06
    _experiment
    0.06
    (app
    0.06
    Activations Density 0.055%

    No Known Activations