© 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. 92530
    Prev
    Next
    INDEX
    Explanations

    system-related statements or claims

    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
    n
    -0.07
    g
    -0.06
    esk
    -0.06
     Per
    -0.06
    en
    -0.06
    at
    -0.05
     Mah
    -0.05
    oslav
    -0.05
     prof
    -0.05
    nam
    -0.05
    POSITIVE LOGITS
     cá»Ń
    0.08
    ãĥ³ãĥĶ
    0.07
    ATIO
    0.07
     доÑģ
    0.07
    itler
    0.07
    ãĥ¼ãĥĹ
    0.07
    _slow
    0.07
    ittle
    0.07
     addCriterion
    0.07
    olie
    0.07
    Activations Density 0.004%

    No Known Activations