© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14452
    Prev
    Next
    INDEX
    Explanations

    references to intermediaries in various contexts

    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
    strand
    -0.07
    ullah
    -0.06
    lit
    -0.06
     #__
    -0.06
    QA
    -0.06
     اÙĦÙħÙĨ
    -0.06
    kad
    -0.06
    odo
    -0.06
     stain
    -0.06
    éĻ
    -0.06
    POSITIVE LOGITS
     intermedi
    0.20
     intermediary
    0.19
     intermediate
    0.15
     Intermediate
    0.12
    medi
    0.12
     mediator
    0.11
    Intermediate
    0.11
     mediation
    0.11
     trung
    0.11
     indirect
    0.11
    Activations Density 0.115%

    No Known Activations