© 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. 107803
    Prev
    Next
    INDEX
    Explanations

    references to selection and choices

    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
    ร
    -0.08
    stk
    -0.08
    atham
    -0.08
    enia
    -0.07
    cestor
    -0.07
    quez
    -0.07
    ansk
    -0.07
    aires
    -0.07
    iceps
    -0.07
    ì·¨
    -0.07
    POSITIVE LOGITS
     lá»įc
    0.08
    ernels
    0.08
    ett
    0.08
    ride
    0.08
    aroo
    0.07
    abee
    0.07
    ling
    0.07
    eson
    0.07
    515
    0.07
    ert
    0.07
    Activations Density 0.015%

    No Known Activations