© 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. 22-LLAMASCOPE-RES-131K
    11. 3857
    Prev
    Next
    INDEX
    Explanations

    references to specific companies and their competitive dynamics

    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
    ErrorException
    -0.07
     yorum
    -0.06
    queeze
    -0.06
    estroy
    -0.06
    Unmarshaller
    -0.06
    orthy
    -0.06
     lookahead
    -0.06
    upt
    -0.06
    ole
    -0.06
    DECL
    -0.06
    POSITIVE LOGITS
     discovered
    0.23
     discover
    0.23
     discovery
    0.22
     discovers
    0.21
     learn
    0.21
     learned
    0.20
     Discover
    0.20
     discovering
    0.20
    Discover
    0.19
     learns
    0.19
    Activations Density 0.045%

    No Known Activations