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. 43771
    Prev
    Next
    INDEX
    Explanations

    references to volunteering opportunities and community service involvement

    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
    .omg
    -0.07
    olini
    -0.07
    PLUGIN
    -0.06
    obar
    -0.06
    ãĤıãģĽ
    -0.06
    ìĹĦ
    -0.06
    عÙĦاÙħ
    -0.06
    elu
    -0.06
    ูà¸ķ
    -0.06
    ochen
    -0.06
    POSITIVE LOGITS
     sorting
    0.09
     cler
    0.09
     greeting
    0.08
     gre
    0.08
     stuffing
    0.08
    Sorting
    0.08
     Sorting
    0.08
     sorter
    0.08
     shel
    0.08
     administrative
    0.08
    Activations Density 0.022%

    No Known Activations