© 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. 804
    Prev
    Next
    INDEX
    Explanations

    phrases related to the scheduling and timing of events

    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
    ÂŃn
    -0.08
    mts
    -0.07
    ekler
    -0.07
    á»iji
    -0.07
    uner
    -0.07
     rowspan
    -0.07
    ستاÙĨ
    -0.07
    .pet
    -0.07
    .wikipedia
    -0.07
    uli
    -0.07
    POSITIVE LOGITS
     sharp
    0.07
    yx
    0.06
    0.06
    _DECL
    0.06
     declared
    0.06
    elan
    0.06
     declaration
    0.06
    riel
    0.06
     declar
    0.06
    nave
    0.05
    Activations Density 0.006%

    No Known Activations