© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 71645
    Prev
    Next
    INDEX
    Explanations

    page

    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
    FA
    -0.08
     saints
    -0.07
     LED
    -0.06
    nier
    -0.06
    ae
    -0.06
    etine
    -0.06
    -times
    -0.06
     Ingredient
    -0.06
     sequencing
    -0.06
    kov
    -0.06
    POSITIVE LOGITS
    (directory
    0.07
     unstable
    0.07
     sprintf
    0.07
    .putInt
    0.06
    =current
    0.06
    .white
    0.06
     -$
    0.06
    (window
    0.06
     fine
    0.06
    Saving
    0.06
    Activations Density 0.001%

    No Known Activations