© 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. 17402
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be."

    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
    ÑĦи
    -0.07
    ÑĦÑĸ
    -0.07
    filer
    -0.07
    ifestyles
    -0.07
    Ob
    -0.06
    izon
    -0.06
    ábado
    -0.06
    Ïĩη
    -0.06
    abilities
    -0.06
    ühr
    -0.06
    POSITIVE LOGITS
    aldi
    0.08
    ald
    0.07
     an
    0.06
    eydi
    0.06
     a
    0.06
     final
    0.06
     sensitive
    0.06
    imd
    0.06
     priv
    0.06
     vain
    0.06
    Activations Density 0.029%

    No Known Activations