© 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
    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. 73414
    Prev
    Next
    INDEX
    Explanations

    hyper

    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
     tá
    -0.07
    Packages
    -0.07
     Carter
    -0.06
     Package
    -0.06
    (nil
    -0.06
    τός
    -0.06
    思い
    -0.06
    ерату
    -0.06
    ोद
    -0.06
     зміни
    -0.06
    POSITIVE LOGITS
     hyper
    0.10
     Hyper
    0.08
    hyper
    0.08
    ERS
    0.07
     INTER
    0.07
    เตอร
    0.07
    .Binary
    0.06
    casecmp
    0.06
     Eric
    0.06
     Forex
    0.06
    Activations Density 0.007%

    No Known Activations