© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    actions involving throwing and movement with a ball

    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
    ver
    -0.06
    ais
    -0.06
    ston
    -0.06
     circum
    -0.06
    qv
    -0.06
     test
    -0.06
    åľį
    -0.06
    tern
    -0.05
    loo
    -0.05
     Test
    -0.05
    POSITIVE LOGITS
    airo
    0.07
    kaar
    0.07
    laughter
    0.07
    ayout
    0.07
    à¸ģำล
    0.07
     airspace
    0.07
    ucz
    0.07
    ÏģÏĮÏĤ
    0.07
     Robbins
    0.07
    execution
    0.07
    Activations Density 0.007%

    No Known Activations