© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62607
    Prev
    Next
    INDEX
    Explanations

    terms related to operational processes and their management

    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
    spect
    -0.07
    acht
    -0.07
    ames
    -0.07
    еÑĢк
    -0.06
     kı
    -0.06
    æī¶
    -0.06
    à¹Ħว
    -0.06
    otti
    -0.06
    icus
    -0.06
    anken
    -0.06
    POSITIVE LOGITS
    365
    0.09
    nement
    0.08
    /testing
    0.08
    /function
    0.07
    -mode
    0.07
    ability
    0.07
    /install
    0.07
    ally
    0.07
    razier
    0.06
    mode
    0.06
    Activations Density 0.019%

    No Known Activations