© 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. 125039
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐style parameter or option names (identifiers for config/function arguments) appearing in code or documentation.

    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
    urse
    -0.07
     precursor
    -0.07
    rians
    -0.07
    OMEM
    -0.06
     enrolled
    -0.06
     roof
    -0.06
     campus
    -0.06
     Criteria
    -0.06
    noise
    -0.06
    Edited
    -0.06
    POSITIVE LOGITS
     �
    0.07
    	opt
    0.06
     تر
    0.06
    ({
↵
    0.06
    (times
    0.06
     wcs
    0.06
     (~(
    0.06
    }/#{
    0.06
     IPCC
    0.06
     شخصية
    0.06
    Activations Density 0.022%

    No Known Activations