© 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. 79554
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software and coding

    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
    sak
    -0.07
    chein
    -0.07
    evin
    -0.07
    olics
    -0.07
    tility
    -0.07
    612
    -0.07
    riad
    -0.07
    askell
    -0.06
    ipers
    -0.06
    коÑĤ
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥ³ãĥĪ
    0.07
    /by
    0.07
    owy
    0.07
    ãĥ¯ãĤ¤ãĥĪ
    0.07
    $__
    0.06
    oplan
    0.06
    oley
    0.06
    人æ°ijåħ±åĴĮåĽ½
    0.06
     Tent
    0.06
    oppable
    0.06
    Activations Density 0.008%

    No Known Activations