© 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. 11-RESID-POST-AA
    11. 57879
    Prev
    Next
    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash

    code snippets and programming-related terminology.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron specifically activates on occurrences of the word “here,” as in the phrase “Sure, here’s a simple….”

    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
     "<?
    -0.06
    iali
    -0.06
    	Simple
    -0.06
    Stage
    -0.06
     ------
    -0.06
    .lastIndexOf
    -0.06
     profitable
    -0.06
     -----
    -0.06
     Mosque
    -0.06
     Pro
    -0.05
    POSITIVE LOGITS
    OLL
    0.07
    评价
    0.07
    URRENCY
    0.07
    ieg
    0.07
     tamam
    0.06
    ring
    0.06
    ायन
    0.06
    漫画
    0.06
    _registry
    0.06
     держав
    0.06
    Activations Density 0.036%

    No Known Activations