© 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. 18209
    Prev
    Next
    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash

    conversations about adventure and having fun.

    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
     compr
    -0.08
    face
    -0.07
    ascal
    -0.07
    ाय
    -0.06
     Loren
    -0.06
    кости
    -0.06
     exposition
    -0.06
    asper
    -0.06
     {?
    -0.06
     Hibernate
    -0.06
    POSITIVE LOGITS
    円
    0.07
    埃
    0.06
     Francie
    0.06
     entityId
    0.06
    _lng
    0.06
    really
    0.06
     düz
    0.06
     Guarantee
    0.06
    cern
    0.06
          ↵
    0.06
    Activations Density 0.002%

    No Known Activations