© 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. 111588
    Prev
    Next
    INDEX
    Explanations

    negative words

    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
     державної
    -0.06
    .currentState
    -0.06
    фі
    -0.06
     METHOD
    -0.06
    Charge
    -0.06
    (grammarAccess
    -0.06
     seus
    -0.06
    _MEMORY
    -0.06
     Interview
    -0.06
     thanked
    -0.06
    POSITIVE LOGITS
    printf
    0.06
    िलन
    0.06
    eliness
    0.06
    لاین
    0.06
    nímu
    0.06
     userId
    0.06
    なが
    0.06
     Mitgli
    0.06
     physically
    0.06
     vždy
    0.06
    Activations Density 0.003%

    No Known Activations