Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 71317
    Prev
    Next
    INDEX
    Explanations

    significant nouns related to formal and critical events or actions

    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
    ooter
    -0.07
    ine
    -0.07
    edge
    -0.06
    uro
    -0.06
    isk
    -0.06
    ottle
    -0.06
     similarly
    -0.06
    chal
    -0.06
    inen
    -0.05
    ä
    -0.05
    POSITIVE LOGITS
    tring
    0.08
     there
    0.08
     ayrıca
    0.07
    there
    0.07
    iges
    0.07
    ascus
    0.07
     Ðļоли
    0.07
    enthal
    0.07
    hma
    0.07
    izzy
    0.06
    Activations Density 0.036%

    No Known Activations