© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    references to scores and competitive events in sports

    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
    coni
    -0.07
    foy
    -0.06
     bootstrap
    -0.06
    à¹īà¸Ńม
    -0.06
    permanent
    -0.06
    ãĥŃãĥ³
    -0.06
    ÙĬØ·
    -0.05
    etri
    -0.05
     filtro
    -0.05
    ë°ľ
    -0.05
    POSITIVE LOGITS
     equal
    0.10
     tied
    0.10
     evenly
    0.10
     deadlock
    0.10
     tie
    0.09
     equality
    0.09
     EQUAL
    0.09
     neither
    0.08
    _EQUAL
    0.08
    amba
    0.08
    Activations Density 0.069%

    No Known Activations