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. 5283
    Prev
    Next
    INDEX
    Explanations

    numerical data or references within the text

    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
     ‘
    -0.07
     equipments
    -0.07
     rag
    -0.06
    omid
    -0.06
     '
    -0.06
    .console
    -0.06
    úi
    -0.06
     mind
    -0.06
     Shack
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
    \Migration
    0.07
     gangbang
    0.07
    _partner
    0.07
    ighton
    0.06
    588
    0.06
    æľ
    0.06
     meanwhile
    0.06
    .MediaType
    0.06
    ropol
    0.06
    ortal
    0.06
    Activations Density 0.000%

    No Known Activations