© 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. 77267
    Prev
    Next
    INDEX
    Explanations

    terminology related to formal definitions and classifications

    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
    .MixedReality
    -0.07
     nomine
    -0.07
    елÑİ
    -0.06
    ARGIN
    -0.06
    irs
    -0.06
    ообÑĢаз
    -0.06
     Nederland
    -0.06
    алÑİ
    -0.06
    enko
    -0.06
    avra
    -0.06
    POSITIVE LOGITS
     رج
    0.07
     for
    0.07
    VarChar
    0.07
    ardy
    0.06
     referring
    0.06
    msgid
    0.06
     given
    0.06
    awi
    0.06
    ocz
    0.06
     اطÙĦ
    0.06
    Activations Density 0.011%

    No Known Activations