© 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. 125732
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or sentence-ending indicators

    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
     therefore
    -0.08
    enk
    -0.07
     Therefore
    -0.07
    Therefore
    -0.07
    nemonic
    -0.06
    ottenham
    -0.06
    .generated
    -0.06
    iq
    -0.06
    ourke
    -0.06
     поÑįÑĤомÑĥ
    -0.06
    POSITIVE LOGITS
    ãģ«ãĤĪ
    0.08
    Spoiler
    0.08
    rowser
    0.08
    plib
    0.07
    irth
    0.07
    indr
    0.07
    ete
    0.07
     Spo
    0.07
    abay
    0.07
    toMatch
    0.06
    Activations Density 0.037%

    No Known Activations