© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129192
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic creation and craftsmanship

    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
     fit
    -0.06
    -
    -0.06
     tick
    -0.06
     cub
    -0.06
     held
    -0.06
     
    -0.05
     participants
    -0.05
    (
    -0.05
     sav
    -0.05
    ui
    -0.05
    POSITIVE LOGITS
    areas
    0.10
     areas
    0.09
     Areas
    0.09
    Areas
    0.09
     spots
    0.08
    輪
    0.08
    spots
    0.08
     áreas
    0.08
    .Rollback
    0.07
     Dün
    0.07
    Activations Density 0.021%

    No Known Activations