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. 27-RESID-POST-AA
    6. 108904
    Prev
    Next
    INDEX
    Explanations

    Semiconductor etching damage

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olis
    -0.07
    Salir
    -0.07
    904
    -0.06
    设
    -0.06
    ivní
    -0.06
    _dic
    -0.06
     disdain
    -0.06
     Tennis
    -0.06
     мом
    -0.06
    anut
    -0.06
    POSITIVE LOGITS
    GIN
    0.07
     ژ
    0.07
    MeasureSpec
    0.07
    MethodBeat
    0.07
     CLR
    0.06
     đẩy
    0.06
     STA
    0.06
    .loadtxt
    0.06
    Fact
    0.06
     realloc
    0.06
    Activations Density 0.034%

    No Known Activations