© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60846
    Prev
    Next
    INDEX
    Explanations

    numeric values and indicators of quantity

    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
    .scalablytyped
    -0.09
    pcodes
    -0.08
    ongyang
    -0.07
     endregion
    -0.07
    ứ
    -0.07
    ainless
    -0.07
     UIWindow
    -0.07
     Beit
    -0.07
    Fcn
    -0.07
    uilt
    -0.07
    POSITIVE LOGITS
     Bob
    0.06
    635
    0.06
    bob
    0.06
     bob
    0.06
    OSC
    0.06
    Bob
    0.06
    cis
    0.06
    432
    0.06
    plers
    0.05
     Ou
    0.05
    Activations Density 0.002%

    No Known Activations