© 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. 27319
    Prev
    Next
    INDEX
    Explanations

    structural elements related to layouts and site organization

    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
    stm
    -0.07
    ngen
    -0.06
    tsky
    -0.06
    /weather
    -0.06
    è§Ĵ
    -0.06
     Folk
    -0.06
    èĨ
    -0.06
    vala
    -0.06
     Inspir
    -0.06
    ิà¸Ħ
    -0.06
    POSITIVE LOGITS
    SingleNode
    0.07
    Ä©nh
    0.07
    rière
    0.07
    ThreadId
    0.07
    .compat
    0.07
    ithe
    0.07
    ubbo
    0.07
    ajor
    0.06
    обÑīе
    0.06
    596
    0.06
    Activations Density 0.000%

    No Known Activations