© 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. 22716
    Prev
    Next
    INDEX
    Explanations

    If

    np_max-act · gemini-2.0-flash

    the steps or processes involved in setting up systems or functions, particularly in a professional or organizational context.

    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
    endants
    -0.07
    Real
    -0.06
    Specify
    -0.06
     programmers
    -0.06
    Teen
    -0.06
     PROCESS
    -0.06
    Mexico
    -0.06
    ustering
    -0.06
     мист
    -0.06
     TERMS
    -0.06
    POSITIVE LOGITS
    ToJson
    0.06
    _SCROLL
    0.06
    ━━━━
    0.06
    (pdf
    0.06
     [
↵
    0.06
    (nullptr
    0.06
    [at
    0.06
    _inner
    0.06
     suyu
    0.06
    GetMapping
    0.06
    Activations Density 0.067%

    No Known Activations