Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34804
    Prev
    Next
    INDEX
    Explanations

    ili

    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
     Şu
    -0.07
     phon
    -0.06
    )Math
    -0.06
     glued
    -0.06
    }}}
    -0.06
     morph
    -0.06
     органи
    -0.06
     Proc
    -0.06
     Fountain
    -0.06
    Teacher
    -0.06
    POSITIVE LOGITS
     الکتر
    0.07
    <
    0.07
    зн
    0.07
     прек
    0.06
    τές
    0.06
     Jersey
    0.06
    时代
    0.06
     etter
    0.06
     breakpoints
    0.06
    จาก
    0.06
    Activations Density 0.020%

    No Known Activations