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. 31-LLAMASCOPE-RES-131K
    6. 44087
    Prev
    Next
    INDEX
    Explanations

    terms related to legal definitions and partnerships

    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
    reta
    -0.07
    klady
    -0.06
    _FALL
    -0.06
    .Operator
    -0.06
     ADVISED
    -0.06
     Vendor
    -0.06
    ÅĻeh
    -0.06
    Ord
    -0.06
     Honour
    -0.06
     Ordinary
    -0.06
    POSITIVE LOGITS
    :↵
    0.09
     dissoci
    0.08
     voting
    0.07
     :↵
    0.07
     articles
    0.07
     shares
    0.07
     nonprofit
    0.07
     domestic
    0.07
     persons
    0.07
     subsection
    0.07
    Activations Density 0.019%

    No Known Activations