© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 105157
    Prev
    Next
    INDEX
    Explanations

    Measurement of effort

    np_max-act · gemini-2.0-flash

    mentions of quantities, measurements, durations, or numeric/statistical information.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -ever
    -0.07
    CESS
    -0.07
     slight
    -0.07
    close
    -0.06
     Barbar
    -0.06
    -ground
    -0.06
     Tess
    -0.06
    -même
    -0.06
     dozen
    -0.06
     definite
    -0.06
    POSITIVE LOGITS
    atabase
    0.06
    __":↵
    0.06
     آموزش
    0.06
     aalborg
    0.06
     puerto
    0.06
    alertView
    0.06
     BÖL
    0.06
    .timestamp
    0.06
    	rv
    0.06
     uygu
    0.06
    Activations Density 0.167%

    No Known Activations