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. 95715
    Prev
    Next
    INDEX
    Explanations

    terms related to health, wellness, and charitable foundations

    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
    UNG
    -0.06
    ething
    -0.06
     grip
    -0.06
     bo
    -0.06
    .DOM
    -0.06
    ÙĪÙģ
    -0.06
    ÃĹ
    -0.06
    urm
    -0.06
     discret
    -0.05
     lay
    -0.05
    POSITIVE LOGITS
    ABCDEFGHIJKLMNOP
    0.07
    ansom
    0.07
    coles
    0.07
    ãĥ¼ãĤ¸
    0.07
    cott
    0.07
    rende
    0.06
    eterminate
    0.06
    é»
    0.06
    tica
    0.06
    ||(
    0.06
    Activations Density 0.001%

    No Known Activations