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. 44143
    Prev
    Next
    INDEX
    Explanations

    mentions of artists and their roles or positions within the art community

    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
    NESS
    -0.07
    inness
    -0.07
    å¹ķ
    -0.06
    $core
    -0.06
     onItemClick
    -0.06
     ÑĩаÑģÑĤ
    -0.06
    اÙĨات
    -0.06
    elper
    -0.06
    ibold
    -0.06
    ør
    -0.05
    POSITIVE LOGITS
    ically
    0.13
    otle
    0.12
    ree
    0.10
    ries
    0.10
    amps
    0.10
     residency
    0.09
     talk
    0.09
    ique
    0.09
     Talk
    0.09
    otel
    0.09
    Activations Density 0.012%

    No Known Activations