© 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. 17417
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or formal actions involving ownership and control of resources

    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
     Moff
    -0.07
    ford
    -0.07
     Yuk
    -0.06
     PROGMEM
    -0.06
     subur
    -0.06
    ague
    -0.06
    gate
    -0.06
    ìĦł
    -0.06
    quer
    -0.06
    comm
    -0.06
    POSITIVE LOGITS
     earlier
    0.10
    /left
    0.07
    edis
    0.07
    eyse
    0.07
    itta
    0.07
    acier
    0.07
     ØŃدÙĬØ«
    0.07
    inya
    0.07
    QRST
    0.07
    ranÃŃ
    0.06
    Activations Density 0.044%

    No Known Activations