© 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. 11-RESID-POST-AA
    11. 72648
    Prev
    Next
    INDEX
    Explanations

    slowly

    np_max-act · gemini-2.0-flash

    explicit and aggressive sexual language.

    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
     added
    -0.07
    غات
    -0.07
     abducted
    -0.07
    enschaft
    -0.07
    _KHR
    -0.06
    867
    -0.06
    Unit
    -0.06
    inging
    -0.06
     Reef
    -0.06
     Abbey
    -0.06
    POSITIVE LOGITS
     slowly
    0.14
     Slow
    0.10
     slow
    0.10
    Slow
    0.10
    慢
    0.09
     slower
    0.08
    _slow
    0.07
     quickly
    0.07
     Tomato
    0.07
    .travel
    0.07
    Activations Density 0.010%

    No Known Activations