© 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. 62112
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes in a document

    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
    ple
    -0.06
     MID
    -0.06
     pres
    -0.06
    368
    -0.06
    mui
    -0.06
    OUS
    -0.06
    oy
    -0.06
    ic
    -0.06
     https
    -0.05
    in
    -0.05
    POSITIVE LOGITS
    òa
    0.08
    .er
    0.08
    okud
    0.08
     sophistic
    0.08
    .onViewCreated
    0.08
    ANC
    0.08
    UIApplicationDelegate
    0.08
     cryst
    0.07
    CONTEXT
    0.07
    WindowTitle
    0.07
    Activations Density 0.011%

    No Known Activations