© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 624
    Prev
    Next
    INDEX
    Explanations

    terms related to calculators and digital assistant 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
    796
    -0.06
    orda
    -0.06
    ç¦
    -0.06
    -we
    -0.06
    ãģIJ
    -0.06
    445
    -0.06
     Elephant
    -0.06
    otine
    -0.06
    .scalablytyped
    -0.05
     оз
    -0.05
    POSITIVE LOGITS
    ä¼ı
    0.07
    ritz
    0.07
     Leather
    0.07
    qw
    0.07
    adal
    0.07
    nds
    0.06
    gnore
    0.06
    اÙĨات
    0.06
    intl
    0.06
    umno
    0.06
    Activations Density 0.002%

    No Known Activations