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. 10140
    Prev
    Next
    INDEX
    Explanations

    say "the number 10"

    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
    ru
    -0.07
     supermarkets
    -0.06
    anker
    -0.06
    orch
    -0.06
    .Info
    -0.06
    ("================
    -0.06
     avg
    -0.06
     (*)
    -0.06
     interven
    -0.06
     INFORMATION
    -0.06
    POSITIVE LOGITS
     successfully
    0.06
       
    0.06
    .Button
    0.06
    *****↵
    0.06
    CASE
    0.06
     Pound
    0.06
    143
    0.06
     مشکلات
    0.06
    entrant
    0.06
    (IOException
    0.06
    Activations Density 0.086%

    No Known Activations