© 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. 38188
    Prev
    Next
    INDEX
    Explanations

    definitions and usage examples

    np_max-act · gemini-2.0-flash

    This neuron consistently lights up on the content words in illustrative example sentences (i.e. the running‐text contexts used to show a word’s usage), rather than on the headword or its gloss.

    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
     Kurul
    -0.06
     GetCurrent
    -0.06
     gốc
    -0.06
    нес
    -0.06
    هور
    -0.06
     abras
    -0.06
     Wohn
    -0.06
     مثال
    -0.06
    vin
    -0.06
     Tables
    -0.06
    POSITIVE LOGITS
    ?)
    0.07
    oe
    0.07
    ?).
    0.07
    KW
    0.06
    icolon
    0.06
     pancakes
    0.06
    _Q
    0.06
     fork
    0.06
     KW
    0.06
    dg
    0.06
    Activations Density 0.023%

    No Known Activations