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. 80993
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    specific technical terms and procedures related to software implementation and configuration.

    oai_token-act-pair · gpt-4o-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
    问题
    -0.07
    _dump
    -0.06
     Plex
    -0.06
    criptions
    -0.06
     Backend
    -0.06
    Soup
    -0.06
     název
    -0.06
     Words
    -0.06
     centralized
    -0.06
     problems
    -0.06
    POSITIVE LOGITS
    Ш
    0.08
     nhau
    0.07
    ۵۰
    0.07
    +b
    0.07
     unlocks
    0.07
     nějak
    0.06
     Protein
    0.06
     tph
    0.06
     cardi
    0.06
    ceil
    0.06
    Activations Density 0.089%

    No Known Activations