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. 11433
    Prev
    Next
    INDEX
    Explanations

    concepts related to training and support in various contexts

    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
    ulle
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
    @nate
    -0.06
    eness
    -0.05
     tetas
    -0.05
     separators
    -0.05
     parte
    -0.05
    _Renderer
    -0.05
    NESS
    -0.05
     feelings
    -0.05
    POSITIVE LOGITS
     regime
    0.11
     system
    0.11
     framework
    0.11
     scheme
    0.10
     regimen
    0.10
     program
    0.10
     plan
    0.10
     platform
    0.10
     package
    0.10
     and
    0.10
    Activations Density 0.091%

    No Known Activations