© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 37096
    Prev
    Next
    INDEX
    Explanations

    Actions being performed

    np_max-act · gemini-2.0-flash

    explicit content involving minors and non-consensual situations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /the
    -0.06
     bone
    -0.06
     contempor
    -0.06
    igos
    -0.06
     greater
    -0.06
     kicker
    -0.06
     clock
    -0.06
     Howard
    -0.06
     Timber
    -0.06
    .DEFAULT
    -0.06
    POSITIVE LOGITS
     ابتدا
    0.06
    Shopping
    0.06
    olecular
    0.06
    δη
    0.06
     dolay
    0.06
    .hs
    0.06
    �试
    0.06
    .Ş
    0.06
     акти
    0.06
     답변
    0.06
    Activations Density 0.017%

    No Known Activations