© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55805
    Prev
    Next
    INDEX
    Explanations

    references to tools and utilities related to software and programming

    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
    -Requested
    -0.08
    akedown
    -0.07
    ::__
    -0.06
     stol
    -0.06
     Ùħؤ
    -0.06
    apiro
    -0.06
    StackSize
    -0.06
    387
    -0.06
    ãĥķãĥĪ
    -0.06
    empo
    -0.06
    POSITIVE LOGITS
     EXEMPLARY
    0.08
     kostenlose
    0.07
    utable
    0.07
     versions
    0.07
    utow
    0.07
    tribute
    0.06
    rium
    0.06
    VERSION
    0.06
    ulator
    0.06
    ohl
    0.06
    Activations Density 0.057%

    No Known Activations