© 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. 56802
    Prev
    Next
    INDEX
    Explanations

    terms related to drilling activities or equipment

    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
    ed
    -0.09
    ements
    -0.08
    ents
    -0.08
    àµį
    -0.07
    ex
    -0.07
    uously
    -0.07
    emen
    -0.06
    ethe
    -0.06
    oot
    -0.06
    -0.06
    POSITIVE LOGITS
    leo
    0.08
     holes
    0.07
    voke
    0.07
    aber
    0.07
    town
    0.06
    ë¡ľ
    0.06
    illos
    0.06
    Ñī
    0.06
     sembl
    0.06
    ums
    0.06
    Activations Density 0.019%

    No Known Activations