© 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. 87465
    Prev
    Next
    INDEX
    Explanations

    phrases related to 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
    ãĥ¼ãĥĨ
    -0.07
     surplus
    -0.06
    ãĥ¼ãĥŃ
    -0.06
    ë³Ħ
    -0.06
    аÑĢаÑĤ
    -0.06
    à¹Ģà¸Ł
    -0.06
     Massive
    -0.05
    upo
    -0.05
    awai
    -0.05
    andır
    -0.05
    POSITIVE LOGITS
    877
    0.07
     ìĥģëĮĢ
    0.07
    Basket
    0.07
     tame
    0.07
    omit
    0.07
     yan
    0.06
    _Of
    0.06
    .semantic
    0.06
     exp
    0.06
    ¯u
    0.06
    Activations Density 0.006%

    No Known Activations