© 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. 4688
    Prev
    Next
    INDEX
    Explanations

    references to practical items and preparations related to events or tasks

    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
    udev
    -0.08
    anke
    -0.07
    害
    -0.07
    eldorf
    -0.07
    олÑİ
    -0.07
    elijk
    -0.07
    iram
    -0.07
    orta
    -0.07
    eldom
    -0.07
    izu
    -0.07
    POSITIVE LOGITS
     Newman
    0.07
    ttp
    0.06
    -type
    0.06
     Thy
    0.06
    यर
    0.06
     portable
    0.06
     camping
    0.06
    Visitor
    0.06
     sticks
    0.06
     gint
    0.06
    Activations Density 0.097%

    No Known Activations