© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    adverbs and phrases indicating methods of operation or presence

    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
    vice
    -0.07
    лаÑģÑĤи
    -0.07
    hiro
    -0.07
    lez
    -0.07
    (strtolower
    -0.07
    âm
    -0.07
    awl
    -0.06
    erea
    -0.06
    OVE
    -0.06
    ाश
    -0.06
    POSITIVE LOGITS
     rather
    0.09
    rather
    0.08
     meaning
    0.07
    /by
    0.07
     Rather
    0.07
     via
    0.07
    çĭIJ
    0.07
    cem
    0.07
    ãģ§ãģ¯ãģªãģı
    0.06
    dana
    0.06
    Activations Density 0.045%

    No Known Activations