© 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. 26898
    Prev
    Next
    INDEX
    Explanations

    expressions indicating speculation or suggestion

    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
    SystemService
    -0.09
    idia
    -0.09
     addCriterion
    -0.08
    -wsj
    -0.08
    @Spring
    -0.07
    iales
    -0.07
    arie
    -0.07
    ÙĬار
    -0.07
    obra
    -0.07
    DonaldTrump
    -0.07
    POSITIVE LOGITS
     possibly
    0.08
     hint
    0.08
     possible
    0.08
     perhaps
    0.07
     maybe
    0.07
     Nin
    0.07
     otherwise
    0.07
     suggest
    0.06
     might
    0.06
     future
    0.06
    Activations Density 0.018%

    No Known Activations