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. 81369
    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_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
     adopts
    -0.07
    oot
    -0.06
    "But
    -0.06
    姆
    -0.06
    “We
    -0.06
    ugg
    -0.06
    arry
    -0.06
    �
    -0.06
    ví
    -0.06
     Sands
    -0.06
    POSITIVE LOGITS
    .);↵
    0.07
    .Full
    0.07
    exampleInput
    0.07
     disag
    0.07
    _tokens
    0.06
    (struct
    0.06
     Assert
    0.06
    ")},↵
    0.06
    secutive
    0.06
    _PED
    0.06
    Activations Density 0.192%

    No Known Activations