© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119409
    Prev
    Next
    INDEX
    Explanations

    instructions for customer support and booking modifications

    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
    æ²¢
    -0.07
     Volk
    -0.07
    onth
    -0.07
    çģ½
    -0.06
    /null
    -0.06
    _fwd
    -0.06
     Delivery
    -0.06
    chains
    -0.06
    aud
    -0.06
    tti
    -0.06
    POSITIVE LOGITS
     toll
    0.09
     customer
    0.08
     live
    0.08
     Toll
    0.08
     chat
    0.08
     Customer
    0.08
     support
    0.08
     NotSupportedException
    0.07
     LIVE
    0.07
     Live
    0.07
    Activations Density 0.028%

    No Known Activations