© 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. 43378
    Prev
    Next
    INDEX
    Explanations

    Sm

    np_max-act · gemini-2.0-flash

    the character sequence "Sm" at the start of words (i.e., tokens beginning with "Sm").

    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
     ddl
    -0.07
     wrongdoing
    -0.07
     restrictive
    -0.06
     Terrain
    -0.06
     получения
    -0.06
    ########################################################
    -0.06
    #----------------------------------------------------------------
    -0.06
     revelation
    -0.06
     pollen
    -0.06
     dors
    -0.06
    POSITIVE LOGITS
     Smith
    0.11
     Sm
    0.10
    Smith
    0.09
    Sm
    0.08
    SM
    0.08
     sm
    0.07
     SM
    0.07
    Frank
    0.07
    sm
    0.07
    solid
    0.07
    Activations Density 0.055%

    No Known Activations