© 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 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. 86148
    Prev
    Next
    INDEX
    Explanations

    Question answering snippets

    np_max-act · gemini-2.0-flash

    the neuron's primary trigger is cautionary or safety-focused assistant language—phrases giving warnings, ethical guidance, or moderation/safety advice.

    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
    statuses
    -0.07
    樹
    -0.07
    케이
    -0.07
     Atom
    -0.07
    _IS
    -0.07
    ularity
    -0.06
    žit
    -0.06
    θεί
    -0.06
    bps
    -0.06
    =text
    -0.06
    POSITIVE LOGITS
     πρα
    0.07
     fran
    0.06
    της
    0.06
     adc
    0.06
     Grace
    0.06
    _terms
    0.06
     Necklace
    0.06
    .middle
    0.06
    Der
    0.06
     landscape
    0.06
    Activations Density 0.143%

    No Known Activations