© 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 EvalsExportsinterp-engineNEWAPI 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. 30957
    Prev
    Next
    INDEX
    Explanations

    sections of code or documentation related to class definitions and their organization

    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
    at
    -0.06
    ÙĥÙĪÙĨ
    -0.06
     عÙĤ
    -0.06
    ivi
    -0.06
    heim
    -0.06
    ana
    -0.06
    ihan
    -0.06
    ait
    -0.06
    aho
    -0.06
     roy
    -0.06
    POSITIVE LOGITS
    ~-~-~-~-
    0.07
    efeller
    0.07
    ackbar
    0.07
    å¹¹ç·ļ
    0.07
    unker
    0.06
    vider
    0.06
    uzzi
    0.06
    INLINE
    0.06
    ãĥ£
    0.06
    azers
    0.06
    Activations Density 0.004%

    No Known Activations