© 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. 117407
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidelines and criteria for evaluation

    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
    asion
    -0.07
    dance
    -0.07
     Harding
    -0.06
    ogan
    -0.06
     Alexis
    -0.06
    بار
    -0.06
    eyer
    -0.06
    893
    -0.06
    -urlencoded
    -0.06
     ÐĴики
    -0.06
    POSITIVE LOGITS
     merely
    0.12
    åıªæĺ¯
    0.10
     mere
    0.09
     示
    0.08
    示
    0.08
    bjerg
    0.07
    ä»ħ
    0.07
     guide
    0.07
     intended
    0.07
     only
    0.07
    Activations Density 0.026%

    No Known Activations