© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3825
    Prev
    Next
    INDEX
    Explanations

    mathematical commands and structures in a document

    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
     grunt
    -0.07
     γλη
    -0.06
    ová
    -0.06
    onne
    -0.06
    ities
    -0.06
    oret
    -0.06
    ικο
    -0.06
    port
    -0.06
    olute
    -0.06
    ous
    -0.05
    POSITIVE LOGITS
    eck
    0.08
    posables
    0.07
     Sunder
    0.06
     McInt
    0.06
    dsa
    0.06
     HttpNotFound
    0.06
     دÙĦ
    0.06
    íķ©
    0.06
    egen
    0.06
    irate
    0.06
    Activations Density 0.232%

    No Known Activations