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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 942
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the performance or evaluation of entities or systems

    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
    oram
    -0.08
    pais
    -0.08
    .cv
    -0.08
    arpa
    -0.08
    prite
    -0.08
    .EventHandler
    -0.08
    elon
    -0.08
    ffset
    -0.07
    orget
    -0.07
    nero
    -0.07
    POSITIVE LOGITS
     performance
    0.11
     performances
    0.09
     Performance
    0.08
    performance
    0.08
    Performance
    0.07
     Poh
    0.07
     against
    0.07
     perform
    0.07
    -performance
    0.07
     differently
    0.07
    Activations Density 0.022%

    No Known Activations