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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 128250
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    It detects explicit answers or reply phrases in Q&A-style text (e.g., “the answer is”, “yes”, short declarative responses).

    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
     fathers
    -0.06
     एस
    -0.06
    setValue
    -0.06
     led
    -0.06
     cognitive
    -0.06
     dividend
    -0.06
     Died
    -0.06
    상을
    -0.06
     amis
    -0.06
     battery
    -0.06
    POSITIVE LOGITS
     Valor
    0.07
    Valor
    0.06
    OUNT
    0.06
    časí
    0.06
    /cpp
    0.06
    “你
    0.06
    sburg
    0.06
    /button
    0.06
    습니다
    0.06
    umno
    0.06
    Activations Density 0.309%

    No Known Activations