Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 55657
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words that flag or describe harmful, offensive, or toxic content.

    oai_token-act-pair · o4-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
     painters
    -0.07
     благ
    -0.07
    -depend
    -0.06
     foi
    -0.06
    -info
    -0.06
    /l
    -0.06
     обст
    -0.06
    [var
    -0.06
    ávis
    -0.06
     επί
    -0.06
    POSITIVE LOGITS
    isha
    0.07
    átek
    0.07
    ιλ
    0.07
    emie
    0.06
    (times
    0.06
     холод
    0.06
    ائع
    0.06
     AMD
    0.06
    gere
    0.06
    режд
    0.06
    Activations Density 0.028%

    No Known Activations