© 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. 124480
    Prev
    Next
    INDEX
    Explanations

    references to roles or titles within organizations

    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
    andise
    -0.09
    ihar
    -0.08
    esel
    -0.08
     ÎĶε
    -0.07
    پس
    -0.07
    adelphia
    -0.07
    hung
    -0.07
    æ³°
    -0.07
    ohan
    -0.07
    ORIZONTAL
    -0.07
    POSITIVE LOGITS
     the
    0.06
     President
    0.06
     Professor
    0.06
    ONTAL
    0.06
     tard
    0.05
     bills
    0.05
    ctor
    0.05
    inode
    0.05
     both
    0.05
     surveyed
    0.05
    Activations Density 0.008%

    No Known Activations