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. 23-RESID-POST-AA
    6. 103656
    Prev
    Next
    INDEX
    Explanations

    computational

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("~
    -0.07
    customerId
    -0.07
    ["_
    -0.07
     Smith
    -0.07
    Ken
    -0.06
     Alexander
    -0.06
    71
    -0.06
     пись
    -0.06
    stores
    -0.06
     Ben
    -0.06
    POSITIVE LOGITS
    unal
    0.06
     пару
    0.06
     habil
    0.06
    ichen
    0.06
    .updated
    0.06
     tư
    0.06
    jem
    0.06
    unlock
    0.06
    Actual
    0.06
    vol
    0.06
    Activations Density 0.004%

    No Known Activations