© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 60353
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    馬
    -0.07
     guns
    -0.06
    rowave
    -0.06
     Helpful
    -0.06
    يدة
    -0.06
    cko
    -0.06
    ander
    -0.06
     appar
    -0.06
    μά
    -0.06
     چین
    -0.05
    POSITIVE LOGITS
    mdir
    0.07
    instanc
    0.07
    .Strict
    0.07
     zest
    0.07
    realloc
    0.06
    Req
    0.06
     AMC
    0.06
    
    0.06
     calloc
    0.06
     supplementary
    0.06
    Activations Density 0.011%

    No Known Activations