© 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. 93796
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical symbols

    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
    LOCKS
    -0.08
    deme
    -0.08
    olet
    -0.07
    anton
    -0.07
    kir
    -0.07
    ldre
    -0.07
    adera
    -0.07
    ulaire
    -0.07
    iegel
    -0.07
    akter
    -0.07
    POSITIVE LOGITS
    vron
    0.06
     charge
    0.06
     ±
    0.06
     Alam
    0.06
    nes
    0.06
     taken
    0.06
     Lace
    0.05
    ษ
    0.05
    alsy
    0.05
     Charge
    0.05
    Activations Density 0.037%

    No Known Activations