© 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. 5-LLAMASCOPE-RES-131K
    11. 126091
    Prev
    Next
    INDEX
    Explanations

    references to average values or statistics in discussions

    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
     Bethlehem
    -0.07
    atta
    -0.06
    ials
    -0.06
    j
    -0.06
    baum
    -0.06
    chten
    -0.06
    à¹īม
    -0.06
    elig
    -0.06
    ud
    -0.06
    .edu
    -0.06
    POSITIVE LOGITS
    Lit
    0.07
    ãĤ¶
    0.07
     onDataChange
    0.07
    ONGL
    0.07
    éĶĢ
    0.07
    ì§ĵ
    0.07
     queryInterface
    0.07
    ambia
    0.07
    hurst
    0.06
    ushi
    0.06
    Activations Density 0.007%

    No Known Activations