© 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. 89402
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics or counts

    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
    /pm
    -0.07
     æ¼
    -0.07
    _nsec
    -0.07
    اÙĪÙĬ
    -0.07
    ENE
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    æ¼
    -0.07
     NSLocalizedString
    -0.07
     kav
    -0.07
    íĹĮ
    -0.07
    POSITIVE LOGITS
    aki
    0.08
     thousands
    0.08
     number
    0.07
    ,
    0.06
     Corps
    0.06
     produced
    0.06
     hundreds
    0.06
     Tou
    0.06
     Thousands
    0.06
     numbers
    0.06
    Activations Density 0.020%

    No Known Activations