© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    terms and information related to 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
    logan
    -0.08
    APO
    -0.08
    ĥn
    -0.07
    apo
    -0.07
    arkin
    -0.07
    ÑĢеÑģÑģ
    -0.07
    amel
    -0.07
    lox
    -0.07
    mlin
    -0.07
    ottle
    -0.07
    POSITIVE LOGITS
     _____
    0.06
     tons
    0.06
    kov
    0.05
    Mine
    0.05
     Mine
    0.05
     drag
    0.05
     Reply
    0.05
     Finder
    0.05
     mine
    0.05
     largest
    0.05
    Activations Density 0.014%

    No Known Activations