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. 123424
    Prev
    Next
    INDEX
    Explanations

    File formatting

    np_max-act · gemini-2.0-flash

    Long hexadecimal-like GUIDs or long alphanumeric asset identifiers (serialization GUIDs) in file headers.

    oai_token-act-pair · gpt-5-miniTriggered by @bowenyi
    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
     공간
    -0.07
     Prefix
    -0.06
    Prefix
    -0.06
    stripe
    -0.06
     FORMAT
    -0.06
    arLayout
    -0.06
    へ
    -0.06
    	user
    -0.06
    スティ
    -0.06
      
    -0.06
    POSITIVE LOGITS
     deg
    0.06
    Miss
    0.06
    mute
    0.06
     EDUC
    0.06
     FullName
    0.06
     Miss
    0.06
     Rays
    0.06
     dissolved
    0.06
     fName
    0.06
    予
    0.06
    Activations Density 0.007%

    No Known Activations