© 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. 17-LLAMASCOPE-RES-131K
    6. 40773
    Prev
    Next
    INDEX
    Explanations

    instances of physical movements or changes in position

    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
    ä¸ĺ
    -0.06
    anou
    -0.06
    arp
    -0.06
    gle
    -0.06
    ouz
    -0.06
    _ctor
    -0.06
    IFO
    -0.06
    antu
    -0.06
    alo
    -0.06
     Odd
    -0.06
    POSITIVE LOGITS
    atalog
    0.07
    cca
    0.07
     headed
    0.06
    ãĤ¹ãĤ¿ãĥ¼
    0.06
    ender
    0.06
     prospect
    0.06
    placer
    0.06
     Fixture
    0.06
    180
    0.06
    -heading
    0.06
    Activations Density 0.012%

    No Known Activations