© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 58145
    Prev
    Next
    INDEX
    Explanations

    parameters and values related to function signatures and their definitions 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
     ضÙħÙĨ
    -0.07
    oooo
    -0.07
     ro
    -0.06
    atory
    -0.06
    άÏĥ
    -0.06
    CSR
    -0.06
    ’ÑĹ
    -0.06
     Sud
    -0.06
     no
    -0.06
     b
    -0.06
    POSITIVE LOGITS
    iller
    0.08
    овеÑĢ
    0.08
    <dd
    0.07
    reff
    0.07
    ä¼´
    0.07
     ëĮĢìłĦ
    0.07
    ène
    0.07
     UNUSED
    0.06
    reste
    0.06
    avl
    0.06
    Activations Density 0.024%

    No Known Activations