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. 11-RESID-POST-AA
    6. 21705
    Prev
    Next
    INDEX
    Explanations

    code

    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
    28
    -0.08
    36
    -0.07
    29
    -0.07
    45
    -0.07
    12
    -0.06
    57
    -0.06
    56
    -0.06
     turbulence
    -0.06
    قية
    -0.06
    (OS
    -0.06
    POSITIVE LOGITS
     euth
    0.07
    uzione
    0.07
    uggle
    0.07
     unfairly
    0.06
     ||=
    0.06
    [iVar
    0.06
    .chomp
    0.06
    \Helpers
    0.06
     Argument
    0.06
    vtColor
    0.06
    Activations Density 0.030%

    No Known Activations