© 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. 79589
    Prev
    Next
    INDEX
    Explanations

    mentions of reinforcements or instances of actions related to control and oversight

    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
    ingly
    -0.09
     Cres
    -0.07
    ently
    -0.07
    ÑģÑĤÑİ
    -0.07
    heimer
    -0.06
    евид
    -0.06
    /var
    -0.06
    ioned
    -0.06
    rophe
    -0.06
    coder
    -0.06
    POSITIVE LOGITS
    eping
    0.07
     cá»Ń
    0.07
    /testing
    0.07
    419
    0.06
    844
    0.06
    339
    0.06
     actively
    0.06
    -ie
    0.06
    utherford
    0.06
    disp
    0.06
    Activations Density 0.045%

    No Known Activations