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. 83131
    Prev
    Next
    INDEX
    Explanations

    statistical hypothesis testing

    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
    adc
    -0.08
    Never
    -0.07
     Never
    -0.06
     Buying
    -0.06
     stmt
    -0.06
    ın
    -0.06
     zákon
    -0.06
    Italian
    -0.06
    Ό
    -0.06
     Dance
    -0.06
    POSITIVE LOGITS
    연
    0.07
    .AddParameter
    0.07
     endIndex
    0.07
    .ACCESS
    0.07
     densities
    0.06
    .WebDriver
    0.06
     eBook
    0.06
    .ClientSize
    0.06
    .errorMessage
    0.06
     migrant
    0.06
    Activations Density 0.029%

    No Known Activations