© 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. 1151
    Prev
    Next
    INDEX
    Explanations

    occurrences of key terms related to governance, societal issues, and 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
    entes
    -0.07
    hattan
    -0.07
    eah
    -0.07
    utin
    -0.07
    ente
    -0.07
    eson
    -0.06
    ember
    -0.06
    ENTE
    -0.06
    ternet
    -0.06
    668
    -0.06
    POSITIVE LOGITS
     therefore
    0.30
     thus
    0.23
     accordingly
    0.21
     Therefore
    0.19
    Therefore
    0.18
    thus
    0.18
     donc
    0.18
    åĽłæѤ
    0.18
     thereby
    0.17
     quindi
    0.17
    Activations Density 0.052%

    No Known Activations