© 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. 13404
    Prev
    Next
    INDEX
    Explanations

    miss

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words from Romance‐language passages (French or Italian), i.e. non-English 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
    외
    -0.06
     violations
    -0.06
    Membership
    -0.06
    Sarah
    -0.06
     áreas
    -0.06
     companies
    -0.06
    行业
    -0.06
    Prior
    -0.06
     orta
    -0.06
     promised
    -0.06
    POSITIVE LOGITS
     Falcon
    0.07
     rostlin
    0.06
    шем
    0.06
     thats
    0.06
     closeModal
    0.06
    ソン
    0.06
     českých
    0.06
     multiline
    0.06
     prostituerte
    0.06
     (?)
    0.06
    Activations Density 0.243%

    No Known Activations