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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81275
    Prev
    Next
    INDEX
    Explanations

    key information about animal habitats and diets

    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
     Independent
    -0.07
    .mas
    -0.07
    arget
    -0.06
    resco
    -0.06
    etak
    -0.06
     Congress
    -0.06
     Century
    -0.06
    леж
    -0.06
     Independ
    -0.06
    velle
    -0.06
    POSITIVE LOGITS
     occasionally
    0.07
     occasional
    0.07
     rect
    0.07
    åķ
    0.06
    ì§Ģ
    0.06
     nackte
    0.06
    omet
    0.06
    ManagerInterface
    0.06
    éľ
    0.06
    abb
    0.06
    Activations Density 0.002%

    No Known Activations