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. 80961
    Prev
    Next
    INDEX
    Explanations

    Code snippets and technical writing

    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
    _sequences
    -0.07
     fourn
    -0.07
     オ
    -0.06
    irt
    -0.06
     broken
    -0.06
     corners
    -0.06
    онів
    -0.06
     headaches
    -0.06
     wild
    -0.06
     Rounds
    -0.06
    POSITIVE LOGITS
    ihanna
    0.07
    MAP
    0.07
     если
    0.07
    _UNDEF
    0.07
     mongodb
    0.07
    (PATH
    0.07
     pokemon
    0.06
     manned
    0.06
     مس
    0.06
     awk
    0.06
    Activations Density 0.000%

    No Known Activations