© 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. 56003
    Prev
    Next
    INDEX
    Explanations

    adjust

    np_max-act · gemini-2.0-flash

    This neuron detects decimal number tokens (i.e. numeric values containing a fractional part).

    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
     Rome
    -0.08
     सर
    -0.07
    <|end_of_text|>
    -0.07
     port
    -0.07
     pots
    -0.07
     lineage
    -0.06
    lename
    -0.06
     penn
    -0.06
     cann
    -0.06
     müm
    -0.06
    POSITIVE LOGITS
     adjustment
    0.13
     adjusted
    0.12
     Adjustment
    0.11
     adjust
    0.11
     Adjust
    0.10
     adjusting
    0.10
    adjust
    0.09
    Adjust
    0.09
    Adjusted
    0.09
     adjustments
    0.09
    Activations Density 0.018%

    No Known Activations