© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80097
    Prev
    Next
    INDEX
    Explanations

    =

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    芳
    -0.06
    एक
    -0.06
     gpio
    -0.06
    posix
    -0.06
    .Token
    -0.06
    *pow
    -0.06
     workaround
    -0.06
    +_
    -0.06
     spiral
    -0.06
    .Globalization
    -0.06
    POSITIVE LOGITS
     ARTICLE
    0.07
    andering
    0.07
    COMMON
    0.07
     JDK
    0.06
     muže
    0.06
    Resolution
    0.06
     Παρ
    0.06
    ırlar
    0.06
     Fuß
    0.06
     ";↵↵
    0.06
    Activations Density 0.311%

    No Known Activations