© 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. 62340
    Prev
    Next
    INDEX
    Explanations

    terms related to stamps and stamping

    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
    chet
    -0.07
    ermann
    -0.07
    inders
    -0.07
    ubar
    -0.07
    rgb
    -0.07
    upp
    -0.06
    AMS
    -0.06
    icare
    -0.06
    hci
    -0.06
    estring
    -0.06
    POSITIVE LOGITS
    ede
    0.14
    stamp
    0.08
    eding
    0.08
    .stamp
    0.08
    oe
    0.07
    esco
    0.07
     stamp
    0.07
    wart
    0.07
    eded
    0.07
     Stamp
    0.07
    Activations Density 0.006%

    No Known Activations