© 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. 94680
    Prev
    Next
    INDEX
    Explanations

    terms related to spin interactions and charge conservation 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
    agem
    -0.08
    stroy
    -0.07
    oker
    -0.07
    baugh
    -0.07
    atable
    -0.07
     ion
    -0.07
    egin
    -0.07
    splice
    -0.07
    phinx
    -0.07
    ophy
    -0.07
    POSITIVE LOGITS
    fulness
    0.07
    ful
    0.06
    iw
    0.06
    -related
    0.06
    andy
    0.06
    mates
    0.06
    holders
    0.06
    ings
    0.06
     hereby
    0.06
    field
    0.06
    Activations Density 0.010%

    No Known Activations