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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-RESID-POST-AA
    6. 40601
    Prev
    Next
    INDEX
    Explanations

    Retracting something said

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mej
    -0.08
     writ
    -0.06
    Nos
    -0.06
    底
    -0.06
    atum
    -0.06
    -pdf
    -0.06
    reject
    -0.06
     nos
    -0.06
    ぬ
    -0.06
     measurable
    -0.06
    POSITIVE LOGITS
    mw
    0.07
    creenshot
    0.06
    elsing
    0.06
                                  ↵
    0.06
     вели
    0.06
    907
    0.06
    ://'
    0.06
     일본
    0.06
    Verified
    0.06
     realloc
    0.06
    Activations Density 0.094%

    No Known Activations