© 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. 15-LLAMASCOPE-RES-131K
    11. 89736
    Prev
    Next
    INDEX
    Explanations

    references to previous entries or iterations in a series

    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
    gere
    -0.07
    701
    -0.06
    oge
    -0.06
    ứng
    -0.06
    among
    -0.06
     among
    -0.06
    agens
    -0.06
    ISH
    -0.05
     Adopt
    -0.05
     conce
    -0.05
    POSITIVE LOGITS
    âĦĸâĦĸ
    0.08
    ita
    0.08
    .scalablytyped
    0.08
     #+#
    0.08
    etty
    0.07
    #ad
    0.07
    orney
    0.07
    uforia
    0.07
    TemplateName
    0.07
    ntity
    0.07
    Activations Density 0.017%

    No Known Activations