© 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. 54387
    Prev
    Next
    INDEX
    Explanations

    conjunctions and conjunction-like phrases indicating connections or additive relationships

    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
    æĹıèĩªæ²»
    -0.07
    field
    -0.07
    IPC
    -0.07
    via
    -0.07
    ently
    -0.06
     ÅĻÃŃj
    -0.06
    ulumi
    -0.06
     yön
    -0.06
    440
    -0.06
    ning
    -0.06
    POSITIVE LOGITS
     also
    0.09
     other
    0.09
     equipments
    0.09
     autres
    0.08
    also
    0.08
     others
    0.08
     etc
    0.07
     Doch
    0.07
    ramer
    0.07
     Its
    0.07
    Activations Density 0.092%

    No Known Activations