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. 83023
    Prev
    Next
    INDEX
    Explanations

    references to managing and closing connections or sessions

    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
    outil
    -0.08
    .dsl
    -0.07
    èħ
    -0.07
     Müz
    -0.07
     toler
    -0.07
    PAL
    -0.07
    .Payload
    -0.07
    ÃŃž
    -0.07
    alg
    -0.07
    ãĥ³ãĥĸ
    -0.07
    POSITIVE LOGITS
     release
    0.09
     Release
    0.09
     closing
    0.09
     releasing
    0.09
     released
    0.09
     Closing
    0.08
     closure
    0.08
     releases
    0.08
    )dealloc
    0.07
     Released
    0.07
    Activations Density 0.019%

    No Known Activations