© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73865
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate foundational concepts or structures

    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
    ysa
    -0.09
    LF
    -0.08
    ikel
    -0.08
    vez
    -0.07
    辺
    -0.07
    osg
    -0.07
    aspers
    -0.07
    eyse
    -0.07
    luluk
    -0.07
    менÑĤ
    -0.07
    POSITIVE LOGITS
     principles
    0.11
     premise
    0.10
     principle
    0.09
     Principles
    0.09
     premises
    0.08
     principals
    0.07
     concepts
    0.07
     idea
    0.06
     Principle
    0.06
     concept
    0.06
    Activations Density 0.020%

    No Known Activations