© 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. 73592
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    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
    chia
    -0.07
    ivet
    -0.07
    angep
    -0.07
    tro
    -0.07
    onaut
    -0.06
    ÑģÑĤоÑı
    -0.06
    emes
    -0.06
    onder
    -0.06
     Lah
    -0.06
     norge
    -0.06
    POSITIVE LOGITS
     responsible
    0.10
     Responsible
    0.08
     instrumental
    0.08
    ponsible
    0.07
    ecessary
    0.07
    åħ¼
    0.06
    è´Łè´£
    0.06
     re
    0.06
     hired
    0.06
    éro
    0.06
    Activations Density 0.020%

    No Known Activations