Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43548
    Prev
    Next
    INDEX
    Explanations

    Arabic words or phrases with significant meanings related to procedures or concepts

    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
    marshall
    -0.06
     APIs
    -0.06
    Ú©ÙĨ
    -0.06
    ophobia
    -0.05
     formations
    -0.05
     clicked
    -0.05
    ihad
    -0.05
     whiteColor
    -0.05
    utta
    -0.05
     schemes
    -0.05
    POSITIVE LOGITS
     action
    0.12
     notifies
    0.11
    action
    0.09
     owner
    0.09
    _action
    0.09
    -action
    0.09
     Action
    0.09
    _ACTION
    0.09
    'action
    0.09
    .action
    0.09
    Activations Density 0.002%

    No Known Activations