© 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. 17-LLAMASCOPE-RES-131K
    11. 57669
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sources of information or knowledge

    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
    iveau
    -0.08
    åĿĤ
    -0.07
    apon
    -0.07
    ezi
    -0.07
    ollen
    -0.07
    elyn
    -0.07
    esti
    -0.07
    ëĿ¼ëıĦ
    -0.07
    Forgery
    -0.07
    ipay
    -0.07
    POSITIVE LOGITS
     reading
    0.08
     sources
    0.07
     experience
    0.07
     direct
    0.07
     watching
    0.06
    esan
    0.06
     other
    0.06
     experiences
    0.06
     bitter
    0.06
     overhe
    0.06
    Activations Density 0.028%

    No Known Activations