© 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. 2839
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and logical operators

    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
    OffsetTable
    -0.09
    actionDate
    -0.09
    UsageId
    -0.09
    ÏĦαÏĤ
    -0.09
    _mE
    -0.09
    .scalablytyped
    -0.09
    lexport
    -0.09
    _mD
    -0.09
    mPid
    -0.09
    /DD
    -0.08
    POSITIVE LOGITS
    /or
    0.09
     non
    0.07
    olan
    0.07
    ones
    0.07
    agen
    0.07
     semi
    0.07
    da
    0.06
     re
    0.06
     special
    0.06
     “
    0.06
    Activations Density 0.039%

    No Known Activations