© 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. 83184
    Prev
    Next
    INDEX
    Explanations

    temporal markers and historical 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
    aved
    -0.07
    áf
    -0.06
    ohl
    -0.06
    cheid
    -0.06
    catid
    -0.06
    orrar
    -0.06
    ertino
    -0.06
    ichert
    -0.06
    scenes
    -0.06
    ifton
    -0.06
    POSITIVE LOGITS
     Census
    0.09
     census
    0.09
     popis
    0.07
     Enumerator
    0.07
     enumerator
    0.07
    orden
    0.07
    _NR
    0.07
     household
    0.07
    ì´Īëĵ±íķĻêµIJ
    0.07
    çijŁ
    0.06
    Activations Density 0.002%

    No Known Activations