© 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. 39040
    Prev
    Next
    INDEX
    Explanations

    references to programs, initiatives, or organizations associated with governmental or environmental themes

    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
    ÅĤug
    -0.08
    ulace
    -0.07
    aç
    -0.07
    iming
    -0.06
    ÌĨ
    -0.06
     terminal
    -0.06
    Terminal
    -0.06
    ολ
    -0.06
    tras
    -0.06
    terminal
    -0.06
    POSITIVE LOGITS
    ãĥ§
    0.07
    orum
    0.07
    ¢
    0.06
     SOS
    0.06
    088
    0.06
     bian
    0.06
    ROC
    0.06
    .LENGTH
    0.06
    (chan
    0.06
     htt
    0.05
    Activations Density 0.019%

    No Known Activations