© 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. 118731
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or institutions related to St. Louis

    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
     standards
    -0.07
     destruct
    -0.07
    igue
    -0.07
     Rouge
    -0.06
    ameda
    -0.06
    imbus
    -0.06
     touchdown
    -0.06
    iaux
    -0.06
    struction
    -0.06
    fat
    -0.06
    POSITIVE LOGITS
    (ST
    0.08
    /testify
    0.08
    аниÑĨ
    0.07
    opleft
    0.07
    urtle
    0.07
    bucks
    0.07
    edException
    0.07
    μα
    0.07
    aversable
    0.07
    sWith
    0.07
    Activations Density 0.066%

    No Known Activations