© 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. 26849
    Prev
    Next
    INDEX
    Explanations

    references to literary works and their impact on readers

    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
    ade
    -0.06
    yll
    -0.06
    .shell
    -0.06
     ech
    -0.06
     f
    -0.06
    говоÑĢ
    -0.06
    елÑĮзÑı
    -0.06
    atty
    -0.06
    ledger
    -0.06
    Snapshot
    -0.06
    POSITIVE LOGITS
    oldt
    0.07
     twice
    0.07
    izu
    0.06
    ülük
    0.06
    tea
    0.06
    414
    0.06
    ä¸Ģ度
    0.06
    åľ¨çº¿è§Ĥçľĭ
    0.06
    YLON
    0.06
    .scalablytyped
    0.06
    Activations Density 0.025%

    No Known Activations