© 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. 15-LLAMASCOPE-RES-131K
    11. 88808
    Prev
    Next
    INDEX
    Explanations

    Java code structure and import statements

    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
    lev
    -0.08
    immel
    -0.07
    adius
    -0.06
    bject
    -0.06
    bourg
    -0.06
    cie
    -0.06
    .
    -0.06
     He
    -0.05
     ransom
    -0.05
     Pandora
    -0.05
    POSITIVE LOGITS
    ysics
    0.08
    ãĥ³ãĤ¬
    0.07
    ¬¬
    0.07
    ÑıÑħ
    0.07
    Âłtom
    0.07
    .quality
    0.07
    ãĥ³ãĥIJ
    0.07
    Ñĩно
    0.06
    izzo
    0.06
    uish
    0.06
    Activations Density 0.013%

    No Known Activations