© 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. 119142
    Prev
    Next
    INDEX
    Explanations

    references to page creation and automated processes

    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
    nap
    -0.06
    zen
    -0.06
    apers
    -0.06
     Honey
    -0.06
    .cgi
    -0.06
    vier
    -0.06
     pur
    -0.05
    ãģĹãĤĩãģĨ
    -0.05
    .Framework
    -0.05
    453
    -0.05
    POSITIVE LOGITS
    odata
    0.08
    ãĤ±ãĥĥãĥĪ
    0.07
    Allocator
    0.07
    ouser
    0.07
     ÑģвÑı
    0.07
    λÏĮ
    0.07
    .fromString
    0.07
    ãĥ¼ãĥIJ
    0.07
    å½ķ
    0.07
    isure
    0.07
    Activations Density 0.000%

    No Known Activations