Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 83490
    Prev
    Next
    INDEX
    Explanations

    navbar

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bened
    -0.07
    EDIT
    -0.07
    �
    -0.07
     capsules
    -0.07
    laughter
    -0.06
    dw
    -0.06
    FixedSize
    -0.06
     srpna
    -0.06
     Chemical
    -0.06
    _lm
    -0.06
    POSITIVE LOGITS
     hö
    0.07
    ."[
    0.07
    ;<
    0.06
     navbar
    0.06
    ubern
    0.06
     وي
    0.06
    독
    0.06
     conc
    0.06
    돌
    0.06
    #"
    0.06
    Activations Density 0.000%

    No Known Activations