Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95972
    Prev
    Next
    INDEX
    Explanations

    topics related to medicine and health treatments

    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
     Rei
    -0.08
    isman
    -0.07
    istan
    -0.07
    iped
    -0.07
    otos
    -0.07
    icari
    -0.06
    IVO
    -0.06
    noinspection
    -0.06
    ensa
    -0.06
     Elias
    -0.06
    POSITIVE LOGITS
    505
    0.07
    æĮ¯ãĤĬ
    0.07
    stration
    0.06
    issance
    0.06
     vs
    0.06
    ĥ
    0.06
     WaitForSeconds
    0.06
    à¹ģห
    0.06
    Trace
    0.06
     Balk
    0.06
    Activations Density 0.089%

    No Known Activations