Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29275
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases indicating contrast or exceptions

    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
     Boy
    -0.06
    jur
    -0.06
    childNodes
    -0.06
    emory
    -0.06
     c
    -0.06
     Becker
    -0.06
     Don
    -0.05
    RC
    -0.05
     suppose
    -0.05
    issen
    -0.05
    POSITIVE LOGITS
     Všech
    0.08
    orrent
    0.08
    dee
    0.07
    tok
    0.07
    ToEnd
    0.07
     Resolver
    0.07
    ÙijÙĩ
    0.07
    âĻª
    0.07
    æŀĿ
    0.07
    梨
    0.07
    Activations Density 0.038%

    No Known Activations