© 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. 84334
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to analogies and comparisons

    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
    нимаеÑĤ
    -0.06
    omm
    -0.06
    vé
    -0.05
    rosso
    -0.05
    нима
    -0.05
     Pron
    -0.05
     policies
    -0.05
    elm
    -0.05
    arto
    -0.05
     sor
    -0.05
    POSITIVE LOGITS
     analogy
    0.23
     metaphor
    0.22
     analog
    0.18
     Analog
    0.14
     analogue
    0.13
     metaph
    0.13
     imagery
    0.12
     liken
    0.11
    /met
    0.11
    Met
    0.09
    Activations Density 0.093%

    No Known Activations