© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 89177
    Prev
    Next
    INDEX
    Explanations

    parameters and settings related to temperature and fan control in code

    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
    alars
    -0.08
    ToBounds
    -0.07
    ptrdiff
    -0.07
    ureka
    -0.06
    imler
    -0.06
    olars
    -0.06
    897
    -0.06
    718
    -0.06
    509
    -0.06
    .googleapis
    -0.06
    POSITIVE LOGITS
    99
    0.06
    an
    0.06
     Roland
    0.06
    ãĥ³ãĤ¿
    0.06
    ç»ĩ
    0.06
    zel
    0.06
    CCR
    0.06
    omon
    0.06
     GIT
    0.06
    _mA
    0.06
    Activations Density 0.117%

    No Known Activations