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. 44155
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical or technical parameters and variables

    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
    xit
    -0.06
    -collar
    -0.06
    .xls
    -0.06
    DVD
    -0.06
     dvd
    -0.06
    à¹ĥà¸ļ
    -0.05
     Swords
    -0.05
    indsight
    -0.05
     Dipl
    -0.05
     ÎĿα
    -0.05
    POSITIVE LOGITS
     AMP
    0.22
    AMP
    0.17
     Acceler
    0.14
     Amp
    0.13
     amp
    0.13
    Acceler
    0.13
     accelerated
    0.11
     mobile
    0.11
    _amp
    0.10
     accelerator
    0.10
    Activations Density 0.004%

    No Known Activations