© 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. 11-RESID-POST-AA
    11. 79907
    Prev
    Next
    INDEX
    Explanations

    kind

    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
     Torres
    -0.08
    ￣￣￣￣
    -0.07
    Tai
    -0.07
    902
    -0.07
    tro
    -0.07
    /re
    -0.07
    enez
    -0.07
     ESA
    -0.07
     retrie
    -0.07
     Retrie
    -0.07
    POSITIVE LOGITS
     kind
    0.12
     Kind
    0.10
    kind
    0.10
    Kind
    0.09
     kinds
    0.08
    nd
    0.08
     gdk
    0.08
     KIND
    0.08
    _kind
    0.08
    ind
    0.08
    Activations Density 0.026%

    No Known Activations