© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 101737
    Prev
    Next
    INDEX
    Explanations

    roots

    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
    =item
    -0.06
    vertising
    -0.06
     DEA
    -0.06
    Ken
    -0.06
    bam
    -0.06
    (wrapper
    -0.06
    atype
    -0.06
    сот
    -0.06
     sweat
    -0.06
    !("
    -0.05
    POSITIVE LOGITS
    ное
    0.07
    eneral
    0.07
    덤프
    0.06
    ativas
    0.06
     ","
    0.06
    _coupon
    0.06
     ruthless
    0.06
    .isSuccess
    0.06
     широк
    0.06
    (destination
    0.06
    Activations Density 0.004%

    No Known Activations