© 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. 60955
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in the text

    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
    ADD
    -0.07
    ADDE
    -0.07
    /browse
    -0.07
    /language
    -0.07
    cie
    -0.06
    unifu
    -0.06
    리ìķĦ
    -0.06
    ALER
    -0.06
    eyse
    -0.06
     supervised
    -0.06
    POSITIVE LOGITS
    gu
    0.07
    çķĻ
    0.07
    must
    0.07
    rschein
    0.06
     necessarily
    0.06
     must
    0.06
     cannot
    0.06
    wl
    0.06
    quisite
    0.06
     Cannot
    0.06
    Activations Density 0.000%

    No Known Activations