© 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. 78585
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially periods, which signify the end of statements or thoughts

    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
    年代
    -0.07
    allet
    -0.07
    essa
    -0.07
     pornstar
    -0.06
    acro
    -0.06
    egas
    -0.06
    yle
    -0.06
    YLE
    -0.06
    556
    -0.06
    eur
    -0.06
    POSITIVE LOGITS
     record
    0.08
    orget
    0.08
     demand
    0.07
     unprecedented
    0.07
    Insensitive
    0.07
     cif
    0.07
     sales
    0.07
    endor
    0.07
     Demand
    0.07
    epy
    0.07
    Activations Density 0.041%

    No Known Activations