© 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 EvalsExportsAPI 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. 57372
    Prev
    Next
    INDEX
    Explanations

    symbols indicating jQuery or other programming operations involving elements and events

    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
    ONGL
    -0.08
    alers
    -0.08
    allery
    -0.07
    /max
    -0.07
    utut
    -0.07
    izontally
    -0.07
    mey
    -0.07
    664
    -0.07
     ActionTypes
    -0.07
    lagen
    -0.07
    POSITIVE LOGITS
    ol
    0.06
    ery
    0.06
     exercise
    0.06
    eter
    0.05
     Replay
    0.05
    맨
    0.05
    al
    0.05
    .setDefault
    0.05
     Reign
    0.05
     div
    0.05
    Activations Density 0.002%

    No Known Activations