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. 27-RESID-POST-AA
    6. 73249
    Prev
    Next
    INDEX
    Explanations

    graft

    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
    cka
    -0.08
    hetto
    -0.07
    αλλ
    -0.07
    oblin
    -0.07
    overn
    -0.07
    uard
    -0.07
    ROUP
    -0.07
    libc
    -0.07
     Added
    -0.07
    reeting
    -0.07
    POSITIVE LOGITS
     gaz
    0.10
     GG
    0.10
     gps
    0.10
     GM
    0.09
     gastro
    0.09
     Gauge
    0.09
     GA
    0.09
     GC
    0.09
    _gps
    0.09
     gim
    0.09
    Activations Density 1.386%

    No Known Activations