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

    Neuronpedia

    APICircuit 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. 5508
    Prev
    Next
    INDEX
    Explanations

    references to surface properties or phenomena

    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
    edes
    -0.08
    wd
    -0.08
    748
    -0.07
    oci
    -0.07
    resse
    -0.07
    415
    -0.07
    idas
    -0.07
    944
    -0.07
    .Names
    -0.07
    /wp
    -0.07
    POSITIVE LOGITS
     tension
    0.08
     rough
    0.07
     area
    0.07
     tensions
    0.07
     finish
    0.07
    -mounted
    0.07
    /interface
    0.07
    stations
    0.07
    eware
    0.07
    -to
    0.06
    Activations Density 0.011%

    No Known Activations