© 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. 27670
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" indicating past actions or states

    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
    lech
    -0.06
    ensex
    -0.06
     Claw
    -0.06
    (Un
    -0.06
    ál
    -0.06
     Grace
    -0.06
    alk
    -0.06
    isl
    -0.06
    PBS
    -0.06
    ock
    -0.05
    POSITIVE LOGITS
     preview
    0.07
    uppet
    0.07
    lider
    0.07
    AGIC
    0.07
    aru
    0.07
    اج
    0.07
     previously
    0.06
     Yesterday
    0.06
    दम
    0.06
     yesterday
    0.06
    Activations Density 0.020%

    No Known Activations