© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38419
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects speaker-attribution reporting verbs (like “said,” “says,” “came”) marking quoted or reported speech.

    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
    629
    -0.06
    utzt
    -0.06
     muttered
    -0.06
    edReader
    -0.06
     trả
    -0.05
     lyr
    -0.05
     gắng
    -0.05
     praising
    -0.05
    ibble
    -0.05
     ر
    -0.05
    POSITIVE LOGITS
     secondary
    0.07
     variance
    0.07
     coaching
    0.07
     RAM
    0.07
     tiếp
    0.07
    ERSION
    0.07
     source
    0.06
    street
    0.06
     FRE
    0.06
     commissions
    0.06
    Activations Density 0.016%

    No Known Activations