© 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. 95735
    Prev
    Next
    INDEX
    Explanations

    punctuation and various forms of lists or itemization

    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
    sted
    -0.07
    eyse
    -0.07
    OVE
    -0.07
    rous
    -0.06
    YRO
    -0.06
    ADB
    -0.06
    lle
    -0.06
    272
    -0.06
    zin
    -0.06
    ึ
    -0.06
    POSITIVE LOGITS
     to
    0.09
    HeaderCode
    0.08
     että
    0.08
    _Tis
    0.08
    CallCheck
    0.07
     Äijá»ĥ
    0.07
    VisualStyle
    0.07
    ettings
    0.07
    eson
    0.07
    GuidId
    0.07
    Activations Density 0.016%

    No Known Activations