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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81052
    Prev
    Next
    INDEX
    Explanations

    programming functions and dataframes

    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
    Ch
    -0.07
    (errno
    -0.06
    WISE
    -0.06
    死
    -0.06
    Lat
    -0.06
    谁
    -0.06
    -е
    -0.06
    -es
    -0.06
    ガ
    -0.06
    wh
    -0.06
    POSITIVE LOGITS
    -runtime
    0.08
    uting
    0.07
    τοκ
    0.06
    EditingController
    0.06
    분석
    0.06
    Rails
    0.06
     possono
    0.06
    SeekBar
    0.06
     zamanda
    0.06
    .Menu
    0.06
    Activations Density 0.024%

    No Known Activations