© 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 EvalsExportsAPI 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. 84231
    Prev
    Next
    INDEX
    Explanations

    references to reviews and expert recommendations

    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
    hdl
    -0.07
    endez
    -0.07
    ogl
    -0.07
    avigate
    -0.07
    obil
    -0.07
    plit
    -0.07
    uae
    -0.07
    onth
    -0.07
    ederland
    -0.07
    Č↵
    -0.07
    POSITIVE LOGITS
    ↵
    0.07
    ukan
    0.06
    ï¿
    0.06
     Ellis
    0.06
     Gan
    0.06
    zers
    0.06
    .|
    0.06
     GOODMAN
    0.05
    lish
    0.05
    eter
    0.05
    Activations Density 0.045%

    No Known Activations