© 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. 129790
    Prev
    Next
    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals (integers, decimals, and fractions) within the mathematical 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
     Valid
    -0.07
    cost
    -0.06
    Owner
    -0.06
    professional
    -0.06
    .getCode
    -0.06
     warrant
    -0.06
     desk
    -0.06
     slope
    -0.06
    である
    -0.06
     dosage
    -0.06
    POSITIVE LOGITS
    sin
    0.07
    ysqli
    0.07
    Ì
    0.07
    ány
    0.07
     plated
    0.07
     TextFormField
    0.06
     خو
    0.06
    resizing
    0.06
    े.
    0.06
     합
    0.06
    Activations Density 0.011%

    No Known Activations