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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 80582
    Prev
    Next
    INDEX
    Explanations

    the

    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
     gloves
    -0.07
    772
    -0.07
     infiltr
    -0.07
    altern
    -0.06
     plentiful
    -0.06
    sumer
    -0.06
    ificacion
    -0.06
     Side
    -0.06
     glo
    -0.06
    iffany
    -0.06
    POSITIVE LOGITS
    ائب
    0.07
     başk
    0.07
    PLY
    0.06
    (root
    0.06
    .↵↵↵
    0.06
     Kata
    0.06
     journalistic
    0.06
     procur
    0.06
    ["+
    0.06
    _Format
    0.06
    Activations Density 0.000%

    No Known Activations