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. 44306
    Prev
    Next
    INDEX
    Explanations

    instances of statistical measures and their representation

    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
    ãĤ¤ãĥī
    -0.07
     child
    -0.07
    .child
    -0.07
    imbus
    -0.07
     Autism
    -0.07
    trasound
    -0.07
     nudity
    -0.07
    antha
    -0.07
     autistic
    -0.06
     autism
    -0.06
    POSITIVE LOGITS
     COP
    0.28
    /cop
    0.17
     GOLD
    0.15
     airflow
    0.15
     Cop
    0.14
     cop
    0.14
     smokers
    0.14
    Cop
    0.14
     lung
    0.14
     pulmonary
    0.13
    Activations Density 0.004%

    No Known Activations