© 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. 70243
    Prev
    Next
    INDEX
    Explanations

    references to materials and handling processes in a mining or industrial context

    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
    447
    -0.07
    .cgi
    -0.06
    ASK
    -0.06
     Treasury
    -0.06
    ething
    -0.06
     Snyder
    -0.06
     lav
    -0.06
     <->
    -0.06
    292
    -0.06
    Expanded
    -0.06
    POSITIVE LOGITS
    Rejected
    0.08
    ocha
    0.08
     SORT
    0.07
    eload
    0.07
    _bundle
    0.07
    adir
    0.07
     tractor
    0.07
    çľł
    0.06
    zend
    0.06
    aversable
    0.06
    Activations Density 0.016%

    No Known Activations