© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 113736
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text snippets

    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
    しまった
    -0.07
     alternating
    -0.07
    .requests
    -0.07
     George
    -0.07
     mono
    -0.06
    .erase
    -0.06
     있고
    -0.06
    Mono
    -0.06
     Popular
    -0.06
     البي
    -0.06
    POSITIVE LOGITS
    248
    0.07
     Pf
    0.07
    طب
    0.06
    aye
    0.06
    rung
    0.06
    *h
    0.06
    iddle
    0.06
     outing
    0.06
    Rol
    0.06
    arc
    0.06
    Activations Density 0.011%

    No Known Activations