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. 5423
    Prev
    Next
    INDEX
    Explanations

    references to software and hardware specifications

    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
     रन
    -0.07
     견
    -0.07
     ICMP
    -0.07
    _rp
    -0.07
    MLS
    -0.07
    ryn
    -0.07
    -Sah
    -0.07
    ampion
    -0.07
    ød
    -0.07
     Wilderness
    -0.07
    POSITIVE LOGITS
     channel
    0.07
     tuner
    0.07
     bouquet
    0.07
     programming
    0.07
     satellite
    0.07
     Channel
    0.06
     Tun
    0.06
     Programming
    0.06
    frontend
    0.06
    bou
    0.06
    Activations Density 0.009%

    No Known Activations