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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65871
    Prev
    Next
    INDEX
    Explanations

    disagreement

    np_max-act · gemini-2.0-flash

    This neuron detects Italian-language text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    keywords related to capital punishment and its ethical debates.

    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
    우리
    -0.07
     james
    -0.07
     Ellison
    -0.06
     Shapiro
    -0.06
     Cristiano
    -0.06
     acquitted
    -0.06
     James
    -0.06
     coolest
    -0.06
     Middleware
    -0.06
    �情
    -0.06
    POSITIVE LOGITS
    /l
    0.07
     grenade
    0.06
     U
    0.06
    _alignment
    0.06
    สร
    0.06
    restrict
    0.06
    efully
    0.06
    сим
    0.06
     sniper
    0.06
    ">'
    0.06
    Activations Density 0.055%

    No Known Activations