© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78007
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    specific Python code snippets related to JSON data manipulation.

    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
     Majesty
    -0.07
    addAll
    -0.07
     helpless
    -0.06
     Thorn
    -0.06
    _MASTER
    -0.06
     Peggy
    -0.06
     oldu
    -0.06
     ابزار
    -0.06
    lude
    -0.06
     množství
    -0.06
    POSITIVE LOGITS
    -order
    0.07
    conscious
    0.07
    の方
    0.07
    ，並
    0.07
     öld
    0.06
     स
    0.06
     він
    0.06
    чів
    0.06
    στε
    0.06
    locals
    0.06
    Activations Density 0.021%

    No Known Activations