Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16528
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cost and pricing strategies

    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
    angu
    -0.07
    amber
    -0.07
    erk
    -0.07
    /uploads
    -0.06
    eca
    -0.06
    crollView
    -0.06
    cplusplus
    -0.06
     Welfare
    -0.06
     PROGMEM
    -0.06
    ESSAGES
    -0.06
    POSITIVE LOGITS
     prices
    0.09
     affordable
    0.09
     price
    0.08
    prices
    0.08
    Prices
    0.07
    price
    0.07
     consc
    0.07
     affordability
    0.07
    osu
    0.06
     competitive
    0.06
    Activations Density 0.007%

    No Known Activations