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. 40453
    Prev
    Next
    INDEX
    Explanations

    DDL

    np_max-act · gemini-2.0-flash

    the occurrence of “CDDL” (the license identifier), i.e. the “DDL” substring in license names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    Mayor
    -0.06
    Batman
    -0.06
    iff
    -0.06
    "description
    -0.06
    .IsNullOrEmpty
    -0.06
     Resolution
    -0.06
     απ
    -0.06
     trump
    -0.06
    [prop
    -0.06
    /-
    -0.06
    POSITIVE LOGITS
     CDDL
    0.07
     exhaustion
    0.06
    ITTER
    0.06
    argar
    0.06
     Chill
    0.06
     osobních
    0.06
     Captain
    0.06
     QUICK
    0.06
    Boxes
    0.06
    ौज
    0.06
    Activations Density 0.000%

    No Known Activations