© 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. 70178
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and classes

    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
    ezier
    -0.07
    iasi
    -0.07
    -scrollbar
    -0.07
    ë°©
    -0.07
    idth
    -0.07
    enties
    -0.07
    lify
    -0.07
    ãĥĨãĤ£
    -0.07
    Äįin
    -0.07
    LayoutConstraint
    -0.06
    POSITIVE LOGITS
    rtl
    0.07
    chner
    0.07
    RTL
    0.06
    orie
    0.06
     content
    0.06
     el
    0.06
     left
    0.06
    ÙĪÙĨØ©
    0.06
    umer
    0.06
     chips
    0.06
    Activations Density 0.023%

    No Known Activations