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. 85998
    Prev
    Next
    INDEX
    Explanations

    (c

    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
     sample
    -0.07
    手
    -0.07
    -wrap
    -0.06
    value
    -0.06
     sia
    -0.06
     trees
    -0.06
    here
    -0.06
     generators
    -0.06
     again
    -0.06
    Stra
    -0.06
    POSITIVE LOGITS
    дии
    0.07
    َد
    0.07
    homme
    0.06
     систему
    0.06
    桂
    0.06
     بر
    0.06
     Daughter
    0.06
     physiological
    0.06
     Hispanic
    0.06
    ITTER
    0.06
    Activations Density 0.000%

    No Known Activations