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. 43870
    Prev
    Next
    INDEX
    Explanations

    functional programming elements and structures in the 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
    ritz
    -0.06
    \Controllers
    -0.06
    èīĩ
    -0.05
    idis
    -0.05
    @nate
    -0.05
    chandle
    -0.05
    SingleNode
    -0.05
    .SaveChangesAsync
    -0.05
    irth
    -0.05
    incerely
    -0.05
    POSITIVE LOGITS
     Array
    0.15
     Object
    0.14
     _.
    0.13
     arr
    0.13
    _.
    0.12
     array
    0.12
     Arr
    0.12
    Array
    0.12
     $.
    0.11
    arr
    0.11
    Activations Density 0.028%

    No Known Activations