Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4566
    Prev
    Next
    INDEX
    Explanations

    references to market competition and app platforms

    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
    ÃŃst
    -0.07
    éĻIJ
    -0.07
    Ùħار
    -0.07
     $?
    -0.07
    .twig
    -0.06
    ubern
    -0.06
    ostel
    -0.06
    LOPT
    -0.06
    outu
    -0.06
    YLON
    -0.06
    POSITIVE LOGITS
     usage
    0.10
     popularity
    0.08
     Usage
    0.08
     slice
    0.07
    usage
    0.07
    _usage
    0.07
    Usage
    0.07
    /version
    0.07
     worldwide
    0.07
     adoption
    0.07
    Activations Density 0.002%

    No Known Activations