© 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. 72017
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical transformations and problem-solving solutions

    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
    453
    -0.08
    553
    -0.07
     âĸ³
    -0.07
    oir
    -0.07
    uptools
    -0.07
    YM
    -0.07
    448
    -0.07
    anten
    -0.07
    547
    -0.06
    ÄįÃŃta
    -0.06
    POSITIVE LOGITS
     impossible
    0.11
     difficult
    0.11
     otherwise
    0.11
    Impossible
    0.10
     Impossible
    0.10
     others
    0.10
     previously
    0.09
     diffic
    0.09
     difÃŃcil
    0.09
     difÃŃc
    0.08
    Activations Density 0.033%

    No Known Activations