© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76713
    Prev
    Next
    INDEX
    Explanations

    references to contact information or methods

    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
    ษ
    -0.07
    .Depth
    -0.07
    .Logf
    -0.07
    à¸Ŀ
    -0.07
    $j
    -0.07
    Skeleton
    -0.06
    riminator
    -0.06
     timeouts
    -0.06
    داد
    -0.06
    üzel
    -0.06
    POSITIVE LOGITS
    /contact
    0.08
    -contact
    0.08
     contact
    0.08
    contact
    0.07
     Contact
    0.07
    Contact
    0.06
     contacting
    0.06
    ливÑĸÑģÑĤÑĮ
    0.06
     contacted
    0.06
     CONTACT
    0.06
    Activations Density 0.002%

    No Known Activations