© 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. 28747
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or clubs

    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
    ánh
    -0.06
     chicas
    -0.06
    inge
    -0.06
    аем
    -0.05
     ,
    -0.05
     etc
    -0.05
     of
    -0.05
    itus
    -0.05
     and
    -0.05
     chore
    -0.05
    POSITIVE LOGITS
    ฯ
    0.08
    /MIT
    0.08
    BindingUtil
    0.07
    URA
    0.07
    UrlParser
    0.07
     SPDX
    0.07
    kyt
    0.07
    #__
    0.07
    oders
    0.07
    ãģ£ãģ±ãģĦ
    0.07
    Activations Density 0.016%

    No Known Activations