© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128134
    Prev
    Next
    INDEX
    Explanations

    references to comic books and LGBTQ-themed literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egen
    -0.06
    umi
    -0.06
    ynchronized
    -0.06
    Ñıб
    -0.06
    acl
    -0.06
    oined
    -0.06
    iola
    -0.06
     tit
    -0.06
    ynes
    -0.06
    preter
    -0.06
    POSITIVE LOGITS
    ATUS
    0.07
     lÃłng
    0.07
    onte
    0.07
    emann
    0.07
    èĮĥ
    0.07
    ائÛĮ
    0.06
    %;"
    0.06
    atus
    0.06
    жи
    0.06
    .ToolStrip
    0.06
    Activations Density 0.023%

    No Known Activations