© 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. 130926
    Prev
    Next
    INDEX
    Explanations

    punctuation that signifies endings or separations in the text

    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
    ino
    -0.07
    ib
    -0.06
    itational
    -0.06
    ider
    -0.06
    ache
    -0.06
    ibu
    -0.05
     Wheels
    -0.05
     munch
    -0.05
     Watkins
    -0.05
    's
    -0.05
    POSITIVE LOGITS
    .twitch
    0.08
     kı
    0.08
    ÙĥÙĪÙħ
    0.08
    ìļ¸
    0.07
    ORG
    0.07
    sak
    0.07
    .mdl
    0.07
    escaping
    0.07
    ekl
    0.07
     âĹİ
    0.07
    Activations Density 0.009%

    No Known Activations