© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43383
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens and nearby words that specify the count or listing of categories (e.g. the “5” in “classify into 5 categories”).

    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
     етап
    -0.07
    alah
    -0.07
     hòa
    -0.06
    адж
    -0.06
     nap
    -0.06
    prior
    -0.06
    品
    -0.06
     surve
    -0.06
    grid
    -0.06
    fdc
    -0.06
    POSITIVE LOGITS
     tends
    0.07
    .eth
    0.07
     fighters
    0.07
    ıyorlar
    0.07
    iamo
    0.07
     ordained
    0.06
     organizing
    0.06
    (Api
    0.06
     android
    0.06
    .beans
    0.06
    Activations Density 0.021%

    No Known Activations