© 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. 15-RESID-POST-AA
    11. 26336
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    occurrences of pointer-type annotations in Go code (the '*' and the adjacent type names used in pointer declarations).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (link
    -0.07
    hasil
    -0.07
    _fg
    -0.07
    (on
    -0.07
     thank
    -0.06
     lastname
    -0.06
     occupied
    -0.06
    :x
    -0.06
     который
    -0.06
    °N
    -0.06
    POSITIVE LOGITS
     معمول
    0.07
     빠
    0.06
    .DE
    0.06
     CompletableFuture
    0.06
     Fountain
    0.06
    _-
    0.06
    .false
    0.06
    ricanes
    0.06
     Sub
    0.06
     findViewById
    0.06
    Activations Density 0.002%

    No Known Activations