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. 108864
    Prev
    Next
    INDEX
    Explanations

    Comet assay experiment

    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
    vez
    -0.07
     sauces
    -0.06
    cen
    -0.06
    wich
    -0.06
    cannot
    -0.06
    id
    -0.06
     最
    -0.06
    Grant
    -0.06
    serializer
    -0.06
     competing
    -0.06
    POSITIVE LOGITS
    OLLOW
    0.08
     establishments
    0.07
    물을
    0.07
    .cls
    0.06
     IEntity
    0.06
    宽
    0.06
     widening
    0.06
     Luckily
    0.06
     ModelAndView
    0.06
    .TrimSpace
    0.06
    Activations Density 0.011%

    No Known Activations