© 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. 9-LLAMASCOPE-RES-131K
    11. 98775
    Prev
    Next
    INDEX
    Explanations

    references to legal definitions and conditions regarding exceptional cases and attorney fees

    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
    imitives
    -0.06
     complet
    -0.06
    ostel
    -0.06
    cir
    -0.06
    enso
    -0.06
    .opensource
    -0.06
     HCI
    -0.06
    kel
    -0.06
     pou
    -0.06
    cus
    -0.06
    POSITIVE LOGITS
    udge
    0.07
    Ñĥже
    0.06
    UDGE
    0.06
    ảng
    0.06
     Ñģебе
    0.06
    /Peak
    0.06
    isten
    0.06
    -quality
    0.06
    utsch
    0.06
     Ta
    0.06
    Activations Density 0.036%

    No Known Activations