© 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. 5245
    Prev
    Next
    INDEX
    Explanations

    concepts related to data analysis and comparison

    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
     chứ
    -0.09
     zwar
    -0.07
    ataka
    -0.07
    XMLElement
    -0.07
     (![
    -0.07
    imum
    -0.07
    ingles
    -0.07
    byn
    -0.07
    arella
    -0.07
    ãĤĮ
    -0.06
    POSITIVE LOGITS
     necessarily
    0.10
     ones
    0.08
     merely
    0.08
     anymore
    0.07
    ecessarily
    0.07
    (which
    0.06
    arrow
    0.06
    angi
    0.06
     potentially
    0.06
     Risk
    0.06
    Activations Density 0.052%

    No Known Activations