© 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. 57830
    Prev
    Next
    INDEX
    Explanations

    concepts related to cheering, support, or 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
    avian
    -0.08
    PGA
    -0.07
    affe
    -0.07
    buz
    -0.07
    ifest
    -0.07
    _accessor
    -0.07
    éľĩ
    -0.07
    elope
    -0.07
    843
    -0.07
    åł±
    -0.07
    POSITIVE LOGITS
     emb
    0.07
     team
    0.07
     against
    0.06
     victories
    0.06
     Team
    0.06
     victory
    0.06
     bele
    0.06
     performances
    0.06
    /support
    0.06
     efforts
    0.06
    Activations Density 0.014%

    No Known Activations