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. 43440
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize lessons learned or takeaways from experiences

    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
    annon
    -0.06
    izont
    -0.06
    inct
    -0.06
    inceton
    -0.06
    ekl
    -0.06
    istar
    -0.06
    :animated
    -0.05
    @ResponseBody
    -0.05
    urger
    -0.05
    aiser
    -0.05
    POSITIVE LOGITS
     away
    0.15
    -away
    0.13
    away
    0.12
     home
    0.12
    aways
    0.12
     Away
    0.10
    Away
    0.09
     learn
    0.09
     takeaway
    0.09
     something
    0.09
    Activations Density 0.011%

    No Known Activations