© 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. 126847
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and biological components

    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
    çĽ
    -0.07
    utow
    -0.07
     NSK
    -0.06
    /goto
    -0.06
    stanov
    -0.06
    uld
    -0.06
    CHANNEL
    -0.06
    ë°ĺ
    -0.06
    ulp
    -0.06
    олов
    -0.06
    POSITIVE LOGITS
    rabbit
    0.07
    ãĥ¼ãĥł
    0.06
    legg
    0.06
     touching
    0.06
     respectively
    0.06
     arch
    0.06
    RowCount
    0.06
     Touch
    0.06
    amarin
    0.06
    entina
    0.06
    Activations Density 0.002%

    No Known Activations