© 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. 54340
    Prev
    Next
    INDEX
    Explanations

    terms related to copper and gold mining

    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
    aal
    -0.08
    etus
    -0.07
    .Lookup
    -0.07
     Goodman
    -0.07
    Å¡t
    -0.07
    voke
    -0.06
    alles
    -0.06
     onCancelled
    -0.06
    ellij
    -0.06
    esub
    -0.06
    POSITIVE LOGITS
    -rich
    0.08
    -producing
    0.07
    हन
    0.06
    -bearing
    0.06
    /Math
    0.06
    RunLoop
    0.06
    haft
    0.06
     æŁ
    0.06
    ifer
    0.06
    зÑĭ
    0.06
    Activations Density 0.009%

    No Known Activations