© 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. 39836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or variety

    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
    byname
    -0.06
     pel
    -0.06
    ric
    -0.06
    è²´
    -0.06
     mu
    -0.06
    rico
    -0.05
     MATCH
    -0.05
     match
    -0.05
    ook
    -0.05
    aca
    -0.05
    POSITIVE LOGITS
     different
    0.28
    ä¸įåIJĮçļĦ
    0.23
    different
    0.23
     diferentes
    0.20
     Different
    0.19
    Different
    0.19
    ä¸įåIJĮ
    0.18
     ÑĢазнÑĭÑħ
    0.18
    _different
    0.18
    ifferent
    0.17
    Activations Density 0.049%

    No Known Activations