© 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 EvalsExportsinterp-engineNEWAPI 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. 86649
    Prev
    Next
    INDEX
    Explanations

    adverbs that indicate swift actions or changes

    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
     finally
    -0.09
    aggio
    -0.07
     Finally
    -0.07
    ModelIndex
    -0.07
    Finally
    -0.07
     continu
    -0.07
    ','','
    -0.07
    ç»Īäºİ
    -0.07
    Retention
    -0.07
    _ASSUME
    -0.06
    POSITIVE LOGITS
     become
    0.09
     chóng
    0.09
     became
    0.09
     soon
    0.09
     quickly
    0.09
    zeitig
    0.08
     becomes
    0.08
     Soon
    0.07
    Ĥæķ°
    0.07
    aneously
    0.07
    Activations Density 0.020%

    No Known Activations