© 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. 128427
    Prev
    Next
    INDEX
    Explanations

    references to quarterback performance and related evaluations

    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
    opher
    -0.09
    /goto
    -0.08
    'gc
    -0.08
     огÑĢа
    -0.08
    blr
    -0.07
    acket
    -0.07
    ixel
    -0.07
    Æł
    -0.07
    léd
    -0.07
    é§ħå¾ĴæŃ©
    -0.07
    POSITIVE LOGITS
     among
    0.07
     amongst
    0.07
     at
    0.07
     composition
    0.06
     tslint
    0.06
     personnel
    0.06
     bench
    0.06
     compl
    0.06
     group
    0.06
     depth
    0.06
    Activations Density 0.036%

    No Known Activations