© 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. 27631
    Prev
    Next
    INDEX
    Explanations

    deciding where to eat

    np_max-act · gemini-2.0-flash

    This neuron detects dialogue/speaker-turn language — tokens used in conversational turns, especially first- and second-person pronouns and speaker labels.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    I

    np_max-act · gpt-5-miniTriggered by @yooniel31
    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
    .;
    -0.08
     embraces
    -0.07
    according
    -0.07
    $template
    -0.07
     custody
    -0.07
    .Geometry
    -0.07
    ÔNG
    -0.07
     cuales
    -0.07
    According
    -0.06
    ENSOR
    -0.06
    POSITIVE LOGITS
    theid
    0.07
    álie
    0.06
    ungle
    0.06
     nerv
    0.06
    -prev
    0.06
    eking
    0.06
    rganization
    0.06
    asley
    0.06
    _First
    0.06
    earned
    0.06
    Activations Density 0.107%

    No Known Activations