© 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. 107156
    Prev
    Next
    INDEX
    Explanations

    phrases that express acknowledgment and encouragement

    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
    445
    -0.07
    essor
    -0.06
    amespace
    -0.06
    busters
    -0.06
    angu
    -0.06
    sed
    -0.06
    ieber
    -0.06
    çĦ¶
    -0.06
     thereby
    -0.06
     Crash
    -0.06
    POSITIVE LOGITS
    ñana
    0.08
    ean
    0.07
    леÑĤ
    0.07
     hope
    0.07
    roti
    0.07
     Slee
    0.07
     hoping
    0.06
    urre
    0.06
    .opensource
    0.06
    ersen
    0.06
    Activations Density 0.010%

    No Known Activations