© 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. 11-RESID-POST-AA
    11. 57276
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on punctuation marks and very short or common subword tokens (e.g. dashes, quotes, and brief function‐word fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ',['
    -0.07
     “
    -0.07
     최근
    -0.07
     adresse
    -0.06
    を受
    -0.06
    ：“
    -0.06
    완
    -0.06
    954
    -0.06
    todos
    -0.06
     "
    -0.06
    POSITIVE LOGITS
    ÷
    0.07
    	define
    0.07
    urity
    0.06
    nextInt
    0.06
    ông
    0.06
     founded
    0.06
    lion
    0.06
     flakes
    0.06
     thân
    0.06
    mallow
    0.06
    Activations Density 0.067%

    No Known Activations