© 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. 16687
    Prev
    Next
    INDEX
    Explanations

    rhetorical devices and phrases that imply caution or reminder

    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
    oren
    -0.07
     perhaps
    -0.06
     Anton
    -0.06
    راÙĩ
    -0.06
     VS
    -0.06
     various
    -0.06
    stras
    -0.06
     Ale
    -0.06
     Atl
    -0.05
     versus
    -0.05
    POSITIVE LOGITS
    lds
    0.09
     always
    0.08
    åĩ¡
    0.08
     Always
    0.08
    Remember
    0.08
     Remember
    0.08
    acie
    0.08
    cherche
    0.08
    always
    0.08
    Always
    0.07
    Activations Density 0.026%

    No Known Activations