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. 81199
    Prev
    Next
    INDEX
    Explanations

    yst

    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
     oral
    -0.07
    Rel
    -0.07
     कर
    -0.06
    От
    -0.06
    adors
    -0.06
     сест
    -0.06
    lardı
    -0.06
    LO
    -0.06
     flaw
    -0.06
     lar
    -0.06
    POSITIVE LOGITS
     deficiency
    0.07
    imensional
    0.06
     Zhang
    0.06
    ThemeProvider
    0.06
    ูปแบบ
    0.06
    اضی
    0.06
    μβρίου
    0.06
    observation
    0.06
     million
    0.06
    들의
    0.06
    Activations Density 0.004%

    No Known Activations