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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84343
    Prev
    Next
    INDEX
    Explanations

    references to crafting or knitting projects

    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
    maal
    -0.06
    ainment
    -0.06
    reak
    -0.06
     IMDb
    -0.06
     POV
    -0.06
    asma
    -0.06
    áy
    -0.06
    abi
    -0.06
    eca
    -0.05
     sebou
    -0.05
    POSITIVE LOGITS
    contest
    0.07
    structors
    0.07
    azine
    0.07
     bom
    0.07
     inspir
    0.07
     Instructor
    0.07
    valuator
    0.07
    óst
    0.07
     designs
    0.07
     Instantiate
    0.07
    Activations Density 0.013%

    No Known Activations