© 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. 82504
    Prev
    Next
    INDEX
    Explanations

    references to shoulders or related shoulder attributes

    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
    ACA
    -0.08
    nin
    -0.08
    ways
    -0.08
    _CSR
    -0.07
    åªĴ
    -0.07
    yny
    -0.07
    vara
    -0.07
    vor
    -0.07
    ehir
    -0.07
    vig
    -0.07
    POSITIVE LOGITS
     blades
    0.08
    ered
    0.08
    /back
    0.07
     blade
    0.07
    ocket
    0.07
    stown
    0.06
     Bian
    0.06
    ields
    0.06
    ictory
    0.06
    eron
    0.06
    Activations Density 0.004%

    No Known Activations