© 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. 22-LLAMASCOPE-RES-131K
    11. 4094
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision of something to someone

    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
     riêng
    -0.08
    UILTIN
    -0.08
    lyph
    -0.07
    AGMA
    -0.07
    pt
    -0.07
    005
    -0.07
    eview
    -0.07
    AreaView
    -0.07
     otel
    -0.07
    uju
    -0.06
    POSITIVE LOGITS
     opportunities
    0.10
     opportunity
    0.09
     access
    0.09
     ways
    0.08
     enough
    0.08
     information
    0.08
     choices
    0.07
     insight
    0.07
     a
    0.07
     an
    0.07
    Activations Density 0.020%

    No Known Activations