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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29090
    Prev
    Next
    INDEX
    Explanations

    metaphorical comparisons involving objects and relationships

    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
    assin
    -0.07
     pregn
    -0.07
    orde
    -0.06
    >>)
    -0.06
    (*)(
    -0.06
     Orient
    -0.06
    empre
    -0.06
    Plan
    -0.06
     uranus
    -0.06
    амеÑĤ
    -0.06
    POSITIVE LOGITS
     example
    0.09
     above
    0.09
    ä¾ĭ
    0.08
     those
    0.08
     Above
    0.07
    Above
    0.07
     hypothetical
    0.07
     analogy
    0.07
     Example
    0.07
    .example
    0.07
    Activations Density 0.020%

    No Known Activations