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. 19-RESID-POST-AA
    6. 110606
    Prev
    Next
    INDEX
    Explanations

    Subtitles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     البد
    -0.07
    ARK
    -0.07
     Bobby
    -0.07
     Lt
    -0.06
    Lt
    -0.06
    ADDE
    -0.06
    BER
    -0.06
    _ann
    -0.06
    evaluate
    -0.06
     позитив
    -0.06
    POSITIVE LOGITS
     finance
    0.07
    іл
    0.07
    乎
    0.07
    ivil
    0.06
    台
    0.06
    OutOfRangeException
    0.06
     setPage
    0.06
     migrant
    0.06
    .business
    0.06
    คร
    0.06
    Activations Density 0.002%

    No Known Activations