© 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. 94123
    Prev
    Next
    INDEX
    Explanations

    economic impacts on businesses and industries

    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
    imson
    -0.09
    icine
    -0.07
    unger
    -0.07
    ibold
    -0.07
    unter
    -0.07
    gnore
    -0.07
    .tt
    -0.06
    бÑĥÑĤ
    -0.06
    icina
    -0.06
    icides
    -0.06
    POSITIVE LOGITS
     vital
    0.09
     relied
    0.08
     reliance
    0.08
     rely
    0.08
     reliant
    0.07
     important
    0.07
     relying
    0.07
     integral
    0.07
     relies
    0.07
     abrupt
    0.07
    Activations Density 0.104%

    No Known Activations