© 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. 89726
    Prev
    Next
    INDEX
    Explanations

    INCLUDING

    np_max-act · gemini-2.0-flash

    the uppercase word “INCLUDING” (as it appears in license/disclaimer parentheticals)

    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
     Kant
    -0.07
     diễn
    -0.07
    -е
    -0.06
    .readyState
    -0.06
     Elections
    -0.06
     abusing
    -0.06
    /no
    -0.06
     psych
    -0.06
    Bat
    -0.06
     graduate
    -0.06
    POSITIVE LOGITS
    _param
    0.07
     controls
    0.07
    ="[
    0.06
     モ
    0.06
    なん
    0.06
     delivers
    0.06
     لباس
    0.06
    _LVL
    0.06
     Emacs
    0.06
    λιά
    0.06
    Activations Density 0.001%

    No Known Activations