© 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. 83351
    Prev
    Next
    INDEX
    Explanations

    programming code snippets or technical elements

    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
    EDIUM
    -0.07
    lid
    -0.07
    hait
    -0.07
    ace
    -0.06
    ooter
    -0.06
    apl
    -0.06
    аÑı
    -0.06
    pector
    -0.06
    ingroup
    -0.06
    psz
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.10
    sak
    0.09
    ONTAL
    0.08
    erin
    0.08
    erne
    0.07
    s
    0.07
    ekyll
    0.06
    erus
    0.06
    zelf
    0.06
     Gand
    0.06
    Activations Density 0.019%

    No Known Activations