© 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. 18282
    Prev
    Next
    INDEX
    Explanations

    locations and references to specific places or environments

    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
    rost
    -0.07
    folk
    -0.07
    orsi
    -0.06
    InitialState
    -0.06
    270
    -0.06
     Blow
    -0.06
     blow
    -0.06
    706
    -0.06
    za
    -0.06
    onis
    -0.06
    POSITIVE LOGITS
    reur
    0.07
    åħĭæĸ¯
    0.07
    ured
    0.07
    ourd
    0.06
    ickers
    0.06
    thag
    0.06
    ï¼ĪæĺŃåĴĮ
    0.06
    .getFont
    0.06
    VisualStyle
    0.06
    /******/
    0.06
    Activations Density 0.011%

    No Known Activations