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. 44407
    Prev
    Next
    INDEX
    Explanations

    lines of code and programming-related syntax

    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
    ENOMEM
    -0.06
    _mC
    -0.06
    едж
    -0.05
    UsageId
    -0.05
    HeaderCode
    -0.05
    аÑĤкÑĥ
    -0.05
     fisse
    -0.05
    zent
    -0.05
    .RunWith
    -0.05
    cbd
    -0.05
    POSITIVE LOGITS
     player
    0.33
     players
    0.31
     Player
    0.29
    player
    0.29
     Players
    0.28
    Player
    0.28
    -player
    0.28
    Players
    0.26
    (player
    0.26
    _player
    0.26
    Activations Density 0.022%

    No Known Activations