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. 43671
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to data and statistics

    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
     hugely
    -0.07
     Behaviour
    -0.07
    incy
    -0.07
     tricky
    -0.07
    á»ħ
    -0.06
    Behaviour
    -0.06
     famously
    -0.06
    çĶļèĩ³
    -0.06
    umbo
    -0.06
     Blasio
    -0.06
    POSITIVE LOGITS
     approximately
    0.10
     accident
    0.08
     wreckage
    0.07
     Accident
    0.07
     approximate
    0.07
     subsequent
    0.07
     normal
    0.07
     subsequently
    0.06
    approximately
    0.06
     about
    0.06
    Activations Density 0.003%

    No Known Activations