© 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. 15-LLAMASCOPE-RES-131K
    11. 89976
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components, particularly in chat applications

    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
    owi
    -0.09
    uslim
    -0.08
    ropri
    -0.08
     ãĢľ
    -0.08
    etadata
    -0.07
    itele
    -0.07
    lei
    -0.07
    annies
    -0.07
    urnal
    -0.07
    AIT
    -0.07
    POSITIVE LOGITS
    303
    0.06
     NoSuch
    0.06
    beck
    0.06
     доÑģÑĤ
    0.06
     b
    0.06
     Hell
    0.06
    751
    0.06
     Invocation
    0.06
    247
    0.06
    aller
    0.06
    Activations Density 0.001%

    No Known Activations