© 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. 27389
    Prev
    Next
    INDEX
    Explanations

    terms related to mining and geological exploration

    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
    stre
    -0.07
    ensation
    -0.06
    /functions
    -0.06
     Sort
    -0.05
    okol
    -0.05
    تÙħ
    -0.05
    things
    -0.05
    IFF
    -0.05
    utzer
    -0.05
    861
    -0.05
    POSITIVE LOGITS
     drilling
    0.10
     drill
    0.10
     sond
    0.09
     Depth
    0.09
     bore
    0.09
     drilled
    0.08
     depth
    0.08
    depth
    0.08
     depths
    0.08
    _depth
    0.08
    Activations Density 0.022%

    No Known Activations