© 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. 15-RESID-POST-AA
    11. 23214
    Prev
    Next
    INDEX
    Explanations

    Names/Titles

    np_max-act · gemini-2.0-flash
    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
     Dawson
    -0.08
     braz
    -0.07
    �
    -0.07
    "On
    -0.07
    .Quit
    -0.07
    	comment
    -0.06
    งต
    -0.06
     Roulette
    -0.06
     case
    -0.06
     keypoints
    -0.06
    POSITIVE LOGITS
    f
    0.11
    if
    0.11
    of
    0.10
    SF
    0.10
    F
    0.10
     CF
    0.09
     DF
    0.09
     BF
    0.09
    IF
    0.09
    af
    0.09
    Activations Density 0.519%

    No Known Activations