© 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. 7-RESID-POST-AA
    6. 21230
    Prev
    Next
    INDEX
    Explanations

    hedging and qualifying language

    np_max-act · gemini-2.0-flash

    It detects tokens that signal additional factors, caveats, or contrastive remarks introducing other important considerations.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _light
    -0.07
     mesure
    -0.07
     convolution
    -0.07
    deploy
    -0.07
    aphael
    -0.07
    olest
    -0.07
     Raphael
    -0.07
     adoption
    -0.06
    Rio
    -0.06
     wird
    -0.06
    POSITIVE LOGITS
     clickable
    0.06
    中に
    0.06
    股东
    0.06
    /↵↵
    0.06
    azione
    0.06
    =create
    0.06
     صح
    0.06
     हट
    0.06
     حسن
    0.06
    =a
    0.06
    Activations Density 0.261%

    No Known Activations