© 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. 118446
    Prev
    Next
    INDEX
    Explanations

    objects and materials related to construction and repurposing

    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
     ex
    -0.07
    258
    -0.06
    atta
    -0.06
     only
    -0.06
     at
    -0.06
     sore
    -0.06
    499
    -0.06
     right
    -0.05
     meter
    -0.05
     of
    -0.05
    POSITIVE LOGITS
    -turned
    0.09
    uries
    0.07
    Ïģθ
    0.07
    OLEAN
    0.07
    æĪIJäºĨ
    0.07
    ä½ľä¸º
    0.07
    елÑĮно
    0.07
    ÏĥÏĦά
    0.07
    .syntax
    0.07
    roperties
    0.07
    Activations Density 0.035%

    No Known Activations