© 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 EvalsExportsAPI 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. 88840
    Prev
    Next
    INDEX
    Explanations

    URLs and web-related elements

    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
    @js
    -0.08
    омеÑĢ
    -0.06
    uien
    -0.06
    .appspot
    -0.06
     fres
    -0.06
     Geld
    -0.06
     Variation
    -0.06
     Hüs
    -0.06
    iner
    -0.06
    plier
    -0.06
    POSITIVE LOGITS
    voie
    0.07
    ;charset
    0.07
    ãĥ¼ãĥ©
    0.07
    æŁ´
    0.07
    olders
    0.07
    опиÑģ
    0.06
    oldt
    0.06
    StackNavigator
    0.06
    assa
    0.06
    .standard
    0.06
    Activations Density 0.002%

    No Known Activations