© 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. 79826
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers, likely pertaining to identification or categorization codes

    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
    orado
    -0.08
     quot
    -0.07
    nd
    -0.07
    chten
    -0.07
    gether
    -0.07
    ï¸ı
    -0.07
    ä¸īä¸ī
    -0.07
    quot
    -0.07
    tridge
    -0.07
    adge
    -0.07
    POSITIVE LOGITS
    omore
    0.07
    far
    0.06
    ìĬµ
    0.06
    786
    0.06
    als
    0.06
    DIC
    0.06
     سازÛĮ
    0.06
     Gre
    0.06
    Ãły
    0.05
    ̣
    0.05
    Activations Density 0.025%

    No Known Activations