© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30073
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding player contracts and their value 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
    argout
    -0.08
    antity
    -0.08
     hâl
    -0.08
    ecycle
    -0.08
    tember
    -0.08
    egend
    -0.08
    ÅĻet
    -0.07
     Ulus
    -0.07
    ardu
    -0.07
    rett
    -0.07
    POSITIVE LOGITS
     raw
    0.07
     Unc
    0.07
     prospect
    0.07
    atik
    0.06
    CAPE
    0.06
    unc
    0.06
    Unc
    0.06
    Projection
    0.06
     Value
    0.06
    dot
    0.06
    Activations Density 0.015%

    No Known Activations