© 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. 59772
    Prev
    Next
    INDEX
    Explanations

    occurrences of statistical data or numerical summaries

    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
     nuru
    -0.07
    gets
    -0.07
    enty
    -0.07
     TaÅŁ
    -0.07
    ulant
    -0.06
    achts
    -0.06
    iol
    -0.06
     Vo
    -0.06
    .unsubscribe
    -0.06
    ony
    -0.06
    POSITIVE LOGITS
     yesterday
    0.09
     Yesterday
    0.08
    æĺ¨
    0.07
    Yesterday
    0.07
     today
    0.07
     depuis
    0.06
    rane
    0.06
    Ñģед
    0.06
    ä»ĬæĹ¥
    0.06
     since
    0.06
    Activations Density 0.001%

    No Known Activations