© 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. 5-LLAMASCOPE-RES-131K
    11. 125817
    Prev
    Next
    INDEX
    Explanations

    phrases indicating overall impressions or conclusions

    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
    ele
    -0.07
    znik
    -0.07
    eft
    -0.07
    Ø©
    -0.06
     Hann
    -0.06
    ovich
    -0.06
    áz
    -0.06
    uner
    -0.06
    757
    -0.06
    391
    -0.06
    POSITIVE LOGITS
    .dsl
    0.07
    лÑıÑħ
    0.06
    ellan
    0.06
    0.06
    .AutoScaleMode
    0.06
    adin
    0.06
    gi
    0.06
    Spi
    0.06
     Spi
    0.06
    owell
    0.06
    Activations Density 0.001%

    No Known Activations