© 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. 128997
    Prev
    Next
    INDEX
    Explanations

    dependencies between clauses and conditions within sentences

    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
    ruba
    -0.07
    ez
    -0.06
    irie
    -0.06
    alis
    -0.06
    inke
    -0.06
     Depths
    -0.06
    af
    -0.06
    afd
    -0.06
    enz
    -0.06
    enza
    -0.06
    POSITIVE LOGITS
     ie
    0.13
     ÛĮعÙĨÛĮ
    0.12
     yani
    0.10
     ì¦ī
    0.10
     meaning
    0.10
     ÑĤобÑĤо
    0.10
    meaning
    0.10
    ie
    0.10
    ï¼Įåį³
    0.09
     tức
    0.09
    Activations Density 0.043%

    No Known Activations