© 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. 108334
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and smart technologies

    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
    lea
    -0.06
     Staff
    -0.06
    747
    -0.06
     ul
    -0.06
     Prince
    -0.06
     lipid
    -0.06
     layout
    -0.05
     actionTypes
    -0.05
     rend
    -0.05
    å¯
    -0.05
    POSITIVE LOGITS
    διο
    0.07
    ungeon
    0.07
    untime
    0.07
    conc
    0.07
     Conc
    0.07
     conc
    0.07
     car
    0.07
    _DIAG
    0.07
    icari
    0.07
     пÑĢоб
    0.07
    Activations Density 0.005%

    No Known Activations