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. 44431
    Prev
    Next
    INDEX
    Explanations

    special characters and non-standard symbols

    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
     Sql
    -0.07
    opsy
    -0.07
    quired
    -0.06
    isko
    -0.06
    ahoo
    -0.06
    лÑĥÑĪ
    -0.06
    acock
    -0.06
    ibaba
    -0.06
     PACKET
    -0.06
    ombo
    -0.06
    POSITIVE LOGITS
     UAE
    0.11
     #
    0.10
     Citizen
    0.09
     COVID
    0.09
     '#
    0.09
     Nation
    0.08
     Mother
    0.08
     Campaign
    0.08
    202
    0.08
     campaign
    0.08
    Activations Density 0.004%

    No Known Activations