© 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. 9-LLAMASCOPE-RES-131K
    11. 94928
    Prev
    Next
    INDEX
    Explanations

    instances of displaying or showing information

    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
    SystemService
    -0.08
    alice
    -0.07
    iscopal
    -0.07
    smarty
    -0.06
    μμ
    -0.06
    orc
    -0.06
    ragments
    -0.06
     ac
    -0.06
    urdy
    -0.06
    setattr
    -0.06
    POSITIVE LOGITS
    essian
    0.07
     ValueEventListener
    0.06
    ucks
    0.06
    ITTE
    0.06
    bach
    0.06
    Reserved
    0.06
    iesz
    0.06
    ITIVE
    0.06
    ç¥
    0.06
    ì°©
    0.06
    Activations Density 0.002%

    No Known Activations