© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 68542
    Prev
    Next
    INDEX
    Explanations

    interview text

    np_max-act · gemini-2.0-flash

    sentences or clauses that state facts in the present (marked by high activation on copula "is" and pronouns like "we/you/this").

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iris
    -0.07
    aned
    -0.07
    оны
    -0.06
    _tooltip
    -0.06
    buttons
    -0.06
    >#
    -0.06
     Wiley
    -0.06
    Released
    -0.06
     Equity
    -0.06
    _best
    -0.06
    POSITIVE LOGITS
     chúng
    0.06
     familia
    0.06
     blocking
    0.06
     newState
    0.06
     Dy
    0.06
    ift
    0.06
     Erk
    0.06
     knitting
    0.06
     ''.
    0.06
    ».↵
    0.06
    Activations Density 0.057%

    No Known Activations