© 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. 83044
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions of doubt or uncertainty

    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
    onse
    -0.07
    ÐĬ
    -0.07
    arine
    -0.06
    frontend
    -0.06
    Sensitive
    -0.06
    arme
    -0.06
    cken
    -0.06
    285
    -0.06
     bef
    -0.06
    /frontend
    -0.06
    POSITIVE LOGITS
     try
    0.18
     Try
    0.18
     tries
    0.17
    Try
    0.17
     TRY
    0.17
     tried
    0.17
    try
    0.16
     attempt
    0.16
     Attempt
    0.16
     trying
    0.15
    Activations Density 0.026%

    No Known Activations