© 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. 106421
    Prev
    Next
    INDEX
    Explanations

    financial information related to product pricing

    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
     dil
    -0.06
    gles
    -0.06
     “
    -0.06
     Pastor
    -0.06
     generation
    -0.05
    dent
    -0.05
    ÑĴ
    -0.05
     cold
    -0.05
     mash
    -0.05
     assim
    -0.05
    POSITIVE LOGITS
     (~(
    0.09
    ||(
    0.07
     <$
    0.07
    setWidth
    0.07
    .TabStop
    0.07
    oku
    0.07
    iba
    0.07
    _RT
    0.07
    ावन
    0.07
    ALLED
    0.07
    Activations Density 0.016%

    No Known Activations