© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40130
    Prev
    Next
    INDEX
    Explanations

    transitional words and phrases that indicate contrast or addition

    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
     Horton
    -0.07
    aph
    -0.07
    ef
    -0.06
    ieux
    -0.06
    ant
    -0.06
    iling
    -0.06
    eph
    -0.06
    ieur
    -0.06
    illin
    -0.06
    olo
    -0.06
    POSITIVE LOGITS
    mtime
    0.07
    .createFrom
    0.07
    asses
    0.07
    bsite
    0.07
     cigaret
    0.07
    atég
    0.07
    à¥įयà¤ķ
    0.06
    erton
    0.06
    ypes
    0.06
    subpackage
    0.06
    Activations Density 0.001%

    No Known Activations