© 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. 26918
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational improvement and efficiency

    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
    oldem
    -0.07
    ÑĢоÑĩ
    -0.07
    iaux
    -0.06
     EntityState
    -0.06
     Baker
    -0.06
    ınca
    -0.06
     åıĥ
    -0.06
    ỳ
    -0.06
    jed
    -0.06
    Å¡ak
    -0.06
    POSITIVE LOGITS
     proper
    0.08
    proper
    0.07
     Proper
    0.07
    arnation
    0.07
    urd
    0.07
    elle
    0.06
    ersh
    0.06
     properly
    0.06
    elles
    0.06
     better
    0.06
    Activations Density 0.020%

    No Known Activations