© 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. 26940
    Prev
    Next
    INDEX
    Explanations

    references to organizations and associations related to community and health initiatives

    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
     diá»ĩn
    -0.08
    uite
    -0.07
    loo
    -0.07
    ogan
    -0.07
     vein
    -0.07
    istan
    -0.07
    ece
    -0.06
    лика
    -0.06
    auc
    -0.06
    csi
    -0.06
    POSITIVE LOGITS
     local
    0.09
     locally
    0.09
     regional
    0.08
    local
    0.07
    _Local
    0.07
    _local
    0.07
     Greater
    0.07
     Local
    0.07
     LOCAL
    0.07
     UK
    0.07
    Activations Density 0.122%

    No Known Activations