© 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. 83743
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating connections or relationships in 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
    ums
    -0.08
    aho
    -0.07
    olet
    -0.07
    ToEnd
    -0.06
    gles
    -0.06
    á»ĩu
    -0.06
    eniz
    -0.06
    odash
    -0.06
    oles
    -0.06
    igators
    -0.06
    POSITIVE LOGITS
    RAD
    0.07
    ãĥ³ãĤ¿
    0.06
    Å
    0.06
     ubiqu
    0.06
    KG
    0.06
    %E
    0.06
    emann
    0.06
     Rak
    0.06
    spr
    0.06
    Zoom
    0.06
    Activations Density 0.000%

    No Known Activations