© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    references to tools or resources, particularly related to functionality or categories

    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
    rire
    -0.07
    aal
    -0.06
    .trip
    -0.06
    lass
    -0.06
     syn
    -0.06
    uisse
    -0.05
    v
    -0.05
    aed
    -0.05
    rir
    -0.05
    itt
    -0.05
    POSITIVE LOGITS
    entine
    0.07
    sworth
    0.07
    aria
    0.07
    lag
    0.07
     "('
    0.07
    COPE
    0.07
    atra
    0.07
    serter
    0.07
     Wikimedia
    0.07
     ÐĴики
    0.07
    Activations Density 0.034%

    No Known Activations