Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5439
    Prev
    Next
    INDEX
    Explanations

    concepts related to innovation and creativity

    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
    _sqrt
    -0.07
    adesh
    -0.07
    ipay
    -0.07
    _PREVIEW
    -0.07
    kus
    -0.07
    aleza
    -0.06
    enumerator
    -0.06
    ulle
    -0.06
    ekim
    -0.06
    avou
    -0.06
    POSITIVE LOGITS
     thoughts
    0.15
     Thoughts
    0.13
     about
    0.13
    think
    0.12
     thinks
    0.11
     think
    0.11
     Think
    0.10
    about
    0.10
    Think
    0.10
     thinking
    0.10
    Activations Density 0.017%

    No Known Activations