© 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. 18011
    Prev
    Next
    INDEX
    Explanations

    names or references to notable scholars or researchers

    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
    Ìī
    -0.07
    halt
    -0.07
    shal
    -0.07
    lander
    -0.07
    //{{
    -0.07
    aland
    -0.07
    FULL
    -0.07
    abilia
    -0.06
    rush
    -0.06
    roids
    -0.06
    POSITIVE LOGITS
    ød
    0.09
     Petty
    0.06
    تÙĩا
    0.06
    olle
    0.06
    IFF
    0.06
    ode
    0.06
    ometown
    0.06
    eton
    0.06
     petty
    0.06
    ucker
    0.06
    Activations Density 0.024%

    No Known Activations