© 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. 5039
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminologies related to functions and energy in physics

    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
    avern
    -0.06
    å¼ı
    -0.06
     Barn
    -0.06
     Pig
    -0.06
    atives
    -0.06
     du
    -0.06
    FindObject
    -0.05
     sleepy
    -0.05
     chicken
    -0.05
     Worship
    -0.05
    POSITIVE LOGITS
     spins
    0.07
     occupations
    0.07
     Occupation
    0.06
    hole
    0.06
     Kaplan
    0.06
    AILS
    0.06
    å¤
    0.06
    miner
    0.06
     Ward
    0.06
    omat
    0.06
    Activations Density 0.446%

    No Known Activations