© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    references to cars and motorsport events

    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
     currently
    -0.12
     presently
    -0.10
    currently
    -0.10
    缮åīį
    -0.08
    åĪļæīį
    -0.08
     Currently
    -0.07
    awl
    -0.07
    γη
    -0.07
    Currently
    -0.07
    jedn
    -0.07
    POSITIVE LOGITS
     until
    0.15
    until
    0.13
     Until
    0.11
    Until
    0.11
     eventually
    0.10
     Eventually
    0.10
    _until
    0.10
    Eventually
    0.10
     eventual
    0.10
     hasta
    0.09
    Activations Density 0.076%

    No Known Activations