© 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. 14892
    Prev
    Next
    INDEX
    Explanations

    elements related to publication dates and reviews

    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
     Moy
    -0.06
     comp
    -0.06
    iew
    -0.06
     misc
    -0.06
     post
    -0.06
     vertical
    -0.06
     strict
    -0.06
    uka
    -0.06
     meta
    -0.06
    710
    -0.05
    POSITIVE LOGITS
    à¹ĩà¸Ķ
    0.07
    ADDE
    0.07
     Pod
    0.07
    ipop
    0.07
     \č↵
    0.07
    ÙĤÙĤ
    0.07
     vX
    0.07
    Pod
    0.07
     storyboard
    0.07
    GINE
    0.07
    Activations Density 0.002%

    No Known Activations