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

    Neuronpedia

    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. 40910
    Prev
    Next
    INDEX
    Explanations

    references to various objects and their interactions in a narrative context

    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
    alace
    -0.07
    ateg
    -0.06
    asive
    -0.06
     obtained
    -0.06
    ëĶ°
    -0.06
     addCriterion
    -0.06
    olia
    -0.06
     Gate
    -0.06
     Balt
    -0.06
    elden
    -0.06
    POSITIVE LOGITS
    RunLoop
    0.07
    ixels
    0.07
    ioni
    0.07
    à¸Ńà¸Ļà¸Ĺ
    0.07
    ï¿¥
    0.07
    olle
    0.07
    ixer
    0.06
    üss
    0.06
    activex
    0.06
     from
    0.06
    Activations Density 0.030%

    No Known Activations