© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16770
    Prev
    Next
    INDEX
    Explanations

    ideas and 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
    ogy
    -0.07
    bara
    -0.07
    icket
    -0.06
    otechn
    -0.06
    leo
    -0.06
    HomeAsUp
    -0.06
     mainland
    -0.06
    irable
    -0.06
    ijken
    -0.06
     torrents
    -0.06
    POSITIVE LOGITS
     idea
    0.14
     Idea
    0.12
    idea
    0.11
    .idea
    0.09
     ideas
    0.09
     Ideas
    0.08
     IDEA
    0.08
     concept
    0.07
     ide
    0.07
    ideas
    0.07
    Activations Density 0.019%

    No Known Activations