© 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. 87206
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or questioning

    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
    ibName
    -0.08
    å¹
    -0.07
    ило
    -0.07
    azar
    -0.07
    èĭĹ
    -0.06
    ilo
    -0.06
    ož
    -0.06
     gratuiti
    -0.06
    imar
    -0.06
    tle
    -0.06
    POSITIVE LOGITS
     maybe
    0.07
     how
    0.06
    IA
    0.06
    abe
    0.06
    375
    0.06
     Fu
    0.06
    maybe
    0.06
    ãĤ¤ãĥ¤
    0.06
    abee
    0.06
    endar
    0.06
    Activations Density 0.004%

    No Known Activations