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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125867
    Prev
    Next
    INDEX
    Explanations

    sequences of punctuation or sentence-ending markers

    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
    afs
    -0.07
    رد
    -0.07
    ä¸ĸ
    -0.07
     DÄĽ
    -0.07
    ÐĴÑĸн
    -0.07
     NÄĽm
    -0.07
    ाà¤ķर
    -0.06
     ~(
    -0.06
    ศ
    -0.06
    è̶
    -0.06
    POSITIVE LOGITS
    ORG
    0.09
     Loading
    0.08
     loading
    0.07
    egg
    0.07
    olo
    0.07
    гоÑĢ
    0.06
    rog
    0.06
     Share
    0.06
    razier
    0.06
    @"
    0.06
    Activations Density 0.020%

    No Known Activations