© 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 EvalsExportsAPI 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. 82954
    Prev
    Next
    INDEX
    Explanations

    references to various sports and musical instruments

    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
    echn
    -0.07
    kud
    -0.07
     Fahr
    -0.07
    abase
    -0.07
     Intersection
    -0.07
    cher
    -0.07
    inition
    -0.07
     Richardson
    -0.07
    mart
    -0.06
    ague
    -0.06
    POSITIVE LOGITS
    olu
    0.07
    ersen
    0.07
     at
    0.06
     bare
    0.06
     neat
    0.06
     Dam
    0.06
    -INF
    0.06
     vor
    0.06
     convert
    0.05
     Hal
    0.05
    Activations Density 0.022%

    No Known Activations