© 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. 105200
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with endings or finality

    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
    ulk
    -0.07
    cente
    -0.06
    pv
    -0.06
     ConfigureServices
    -0.06
    emer
    -0.06
    ä¹İ
    -0.06
    عد
    -0.06
    ivr
    -0.06
     mou
    -0.06
    ule
    -0.06
    POSITIVE LOGITS
     till
    0.09
     until
    0.08
     end
    0.08
     square
    0.07
    ê¹Įì§Ģ
    0.07
     minute
    0.07
     bitter
    0.07
     Rak
    0.07
    ÏĦοÏį
    0.06
     endwhile
    0.06
    Activations Density 0.017%

    No Known Activations