© 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. 60555
    Prev
    Next
    INDEX
    Explanations

    headings related to software installation and configuration documentation

    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
    ibri
    -0.08
    esthes
    -0.06
    OA
    -0.06
    é®
    -0.06
    lew
    -0.06
    ,ev
    -0.06
    insky
    -0.06
    yan
    -0.06
     Mik
    -0.06
    olutions
    -0.06
    POSITIVE LOGITS
    .Future
    0.08
    istrovstvÃŃ
    0.08
     future
    0.07
    adol
    0.07
    future
    0.07
    angelog
    0.07
     COPYRIGHT
    0.07
    Future
    0.07
    TestId
    0.07
    _future
    0.06
    Activations Density 0.006%

    No Known Activations