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. 5674
    Prev
    Next
    INDEX
    Explanations

    aspects related to troubleshooting and correcting errors or issues

    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
     Shed
    -0.07
    afka
    -0.07
     Surv
    -0.06
    loff
    -0.06
    _Util
    -0.06
    Surv
    -0.06
    ิà¸ĩ
    -0.06
     Save
    -0.06
     carving
    -0.06
    èĥ
    -0.06
    POSITIVE LOGITS
     rect
    0.19
     fix
    0.17
     resolution
    0.17
     fixes
    0.17
     remed
    0.17
     resolve
    0.17
    fix
    0.16
     remedy
    0.16
    resolve
    0.16
     resolved
    0.16
    Activations Density 0.093%

    No Known Activations