© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56060
    Prev
    Next
    INDEX
    Explanations

    remote

    np_max-act · gemini-2.0-flash

    commands related to managing Git remotes and pruning local references.

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

    The neuron fires on Git “remote” operations—tokens involved in commands like `git remote add …` and `git remote prune …`.

    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
    _odd
    -0.07
     başarı
    -0.06
     Lub
    -0.06
     bringing
    -0.06
     payment
    -0.06
     horr
    -0.06
     kuk
    -0.06
     BLOCK
    -0.06
    'yi
    -0.06
     support
    -0.06
    POSITIVE LOGITS
     رج
    0.07
    �
    0.07
     gratuita
    0.06
    getRequest
    0.06
    .ConnectionStrings
    0.06
    m
    0.06
     �
    0.06
    ını
    0.06
    (raw
    0.06
    human
    0.06
    Activations Density 0.003%

    No Known Activations