© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118684
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intervals or connections between items or events

    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
    onda
    -0.07
    itä
    -0.07
    anner
    -0.07
     hrom
    -0.06
     substitutes
    -0.06
    erge
    -0.06
    EndDate
    -0.06
    zon
    -0.06
    undle
    -0.06
     surrounds
    -0.06
    POSITIVE LOGITS
     each
    0.08
    amarin
    0.07
     periods
    0.07
    isode
    0.07
     times
    0.06
    each
    0.06
     intervals
    0.06
     keer
    0.06
     Kỳ
    0.06
    ded
    0.06
    Activations Density 0.009%

    No Known Activations