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. 81281
    Prev
    Next
    INDEX
    Explanations

    now

    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
    Yesterday
    -0.08
     Rising
    -0.07
    amentals
    -0.07
     realmente
    -0.06
    yang
    -0.06
    .Regular
    -0.06
     Natur
    -0.06
    -shift
    -0.06
    equality
    -0.06
    ον
    -0.06
    POSITIVE LOGITS
    _regions
    0.06
     season
    0.06
    .tb
    0.06
    .PORT
    0.06
    .Flush
    0.06
    EMAIL
    0.06
     predictive
    0.06
    _cn
    0.06
    lex
    0.06
     recognizes
    0.06
    Activations Density 0.185%

    No Known Activations