© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60221
    Prev
    Next
    INDEX
    Explanations

    instances of updates or revisions in a document

    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
    953
    -0.07
    360
    -0.07
    413
    -0.07
    Accessor
    -0.07
    berman
    -0.07
    opak
    -0.07
    adera
    -0.06
    909
    -0.06
    amage
    -0.06
    ulis
    -0.06
    POSITIVE LOGITS
    gnu
    0.08
    BindingUtil
    0.08
    lick
    0.08
    ave
    0.07
    /current
    0.07
    /new
    0.07
    (updated
    0.07
     recently
    0.07
    (update
    0.07
    sik
    0.06
    Activations Density 0.007%

    No Known Activations