© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 51870
    Prev
    Next
    INDEX
    Explanations

    triple

    np_max-act · gemini-2.0-flash

    entities related to cancer treatments and the mechanisms by which they operate.

    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
    ير
    -0.07
    ยาย
    -0.07
    writer
    -0.06
     cocci
    -0.06
    路
    -0.06
     Bea
    -0.06
     Paw
    -0.06
     Circular
    -0.06
     Zar
    -0.06
    ...]↵↵
    -0.06
    POSITIVE LOGITS
     scraps
    0.07
    feat
    0.06
     tackles
    0.06
    recated
    0.06
    emons
    0.06
    331
    0.06
    inyin
    0.06
     y
    0.06
    304
    0.06
    ести
    0.06
    Activations Density 0.004%

    No Known Activations