© 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. 58004
    Prev
    Next
    INDEX
    Explanations

    negative descriptors

    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
    pk
    -0.07
    eg
    -0.06
     kontakte
    -0.06
    umi
    -0.06
    Prompt
    -0.06
    earch
    -0.06
    aises
    -0.06
    ean
    -0.06
    ori
    -0.06
    pty
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
     Throne
    0.07
    /***/
    0.06
    ulent
    0.06
     resent
    0.06
    éĻ¶
    0.06
    á»Ļ
    0.06
     requiring
    0.06
    OperationException
    0.06
    âĨĴâĨĴ
    0.06
    Activations Density 0.000%

    No Known Activations