© 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. 77069
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    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
    gent
    -0.07
    angers
    -0.07
    alk
    -0.06
    ÂŃ
    -0.06
    ÙĪÙĦا
    -0.06
    elm
    -0.06
    lor
    -0.06
    ster
    -0.06
    rollers
    -0.06
    pons
    -0.06
    POSITIVE LOGITS
     currently
    0.10
     now
    0.08
    currently
    0.08
    å°ļ
    0.07
    Currently
    0.07
     Currently
    0.07
    缮åīį
    0.07
    å·²
    0.07
    defer
    0.07
     αÏģ
    0.07
    Activations Density 0.015%

    No Known Activations