Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 122766
    Prev
    Next
    INDEX
    Explanations

    sports standings

    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
    rání
    -0.08
     rf
    -0.07
    ϊκ
    -0.06
    erval
    -0.06
     dán
    -0.06
     draw
    -0.06
     comerc
    -0.06
    _requested
    -0.06
     rahatsız
    -0.06
    iert
    -0.06
    POSITIVE LOGITS
     artic
    0.07
    =post
    0.07
    ُ
    0.06
    )↵↵
    0.06
     Anyway
    0.06
    brief
    0.06
    Piece
    0.06
     onPage
    0.06
     Coloring
    0.06
     :\
    0.06
    Activations Density 0.071%

    No Known Activations