© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76682
    Prev
    Next
    INDEX
    Explanations

    elements related to planning and optimization 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
    pedia
    -0.07
     obdob
    -0.07
    ripper
    -0.07
     bì
    -0.07
     tipping
    -0.07
    .Obj
    -0.07
    .parsers
    -0.07
     tremend
    -0.07
    hled
    -0.07
    ียà¸ģ
    -0.06
    POSITIVE LOGITS
     selected
    0.10
     identified
    0.10
     chosen
    0.10
    Selected
    0.09
    selected
    0.08
    identified
    0.08
     newfound
    0.08
     Identified
    0.08
     newly
    0.07
     determined
    0.07
    Activations Density 0.060%

    No Known Activations