© 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. 126404
    Prev
    Next
    INDEX
    Explanations

    functions related to initialization and cleanup processes in code

    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
    avel
    -0.07
    borough
    -0.07
    OfSize
    -0.07
    .tm
    -0.07
    AndPassword
    -0.07
    isle
    -0.07
    .Builder
    -0.07
    apps
    -0.06
    etes
    -0.06
    -League
    -0.06
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.10
    atter
    0.07
    áze
    0.07
    IPHER
    0.07
    578
    0.06
    ierte
    0.06
     dateFormatter
    0.06
     Cage
    0.06
    èµ·æĿ¥
    0.06
    αιν
    0.06
    Activations Density 0.048%

    No Known Activations