© 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. 26949
    Prev
    Next
    INDEX
    Explanations

    terms related to algorithms and their functionality in computational contexts

    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
    .scalablytyped
    -0.09
    олеÑĤ
    -0.07
    ãĥģãĥ¥
    -0.07
    ÑĦекÑĤив
    -0.07
    लब
    -0.07
    acher
    -0.07
     Ãĸr
    -0.07
     superClass
    -0.07
    oÅĪ
    -0.07
    ültür
    -0.07
    POSITIVE LOGITS
     allowed
    0.06
    avis
    0.06
     tay
    0.06
     Allowed
    0.06
     Information
    0.06
    Å¡k
    0.06
     ste
    0.06
     information
    0.06
     tightly
    0.06
     Sez
    0.06
    Activations Density 0.005%

    No Known Activations