© 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
    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. 29945
    Prev
    Next
    INDEX
    Explanations

    scene

    np_max-act · gemini-2.0-flash

    explicit and adult-oriented content involving sexual themes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron never activates—it does not detect any pattern in the text.

    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
     Jordan
    -0.07
    156
    -0.07
    155
    -0.06
    orent
    -0.06
    _span
    -0.06
    en
    -0.06
     major
    -0.06
     dame
    -0.06
    share
    -0.06
    Uploaded
    -0.06
    POSITIVE LOGITS
     شورای
    0.06
    EntityType
    0.06
     şehir
    0.06
    'nın
    0.06
    oğunluk
    0.06
    fighters
    0.06
     sınav
    0.06
     tí
    0.06
     halinde
    0.06
     náro
    0.06
    Activations Density 0.022%

    No Known Activations