© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78842
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic ethics and related technologies

    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
    INED
    -0.07
     Hlav
    -0.06
     Woche
    -0.06
    rava
    -0.06
     puss
    -0.06
    rama
    -0.06
    CEF
    -0.06
    ãģ¨ãģĭ
    -0.06
     Wyatt
    -0.06
     ìŀĪê³ł
    -0.06
    POSITIVE LOGITS
    564
    0.07
    ellan
    0.07
    alion
    0.07
    ahat
    0.06
    errick
    0.06
    kich
    0.06
     cover
    0.06
    lamaz
    0.06
    ocht
    0.06
    ekil
    0.06
    Activations Density 0.042%

    No Known Activations