© 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. 27493
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    the neuron activates on tokens that are part of proper nouns/company names and numeric specification tokens (e.g., word counts, years, or numbered chemical names).

    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
     清
    -0.07
    -pass
    -0.07
     binder
    -0.06
    Includes
    -0.06
    δί
    -0.06
    ajaran
    -0.06
     Threads
    -0.06
    ffffffff
    -0.06
     denom
    -0.06
     Coh
    -0.06
    POSITIVE LOGITS
    .done
    0.07
    -&
    0.06
    .error
    0.06
    /*↵
    0.06
     trag
    0.06
    �
    0.06
    /************************************************************************************************
    0.06
     अगस
    0.06
    getMockBuilder
    0.06
    _BOUNDS
    0.06
    Activations Density 0.180%

    No Known Activations