© 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. 121080
    Prev
    Next
    INDEX
    Explanations

    coding-related comments and documentation

    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
     splitted
    -0.08
     Levine
    -0.07
     «
    -0.06
    ãĢĮ
    -0.06
    «
    -0.06
     replay
    -0.06
    ima
    -0.06
    UV
    -0.06
     indeed
    -0.06
     actionTypes
    -0.06
    POSITIVE LOGITS
    øj
    0.07
    anders
    0.07
    erro
    0.07
    oui
    0.07
     Sands
    0.06
    .EqualTo
    0.06
    Intialized
    0.06
    aversable
    0.06
    ĵåIJį
    0.06
    ubar
    0.06
    Activations Density 0.031%

    No Known Activations