© 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 EvalsExportsAPI 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. 118732
    Prev
    Next
    INDEX
    Explanations

    elements related to technology and software functionality

    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
     âĹĦ
    -0.09
    istrovstvÃŃ
    -0.07
    culus
    -0.07
    beits
    -0.07
    sterdam
    -0.07
    arent
    -0.07
     Thrones
    -0.07
    olet
    -0.07
    agra
    -0.06
    agrid
    -0.06
    POSITIVE LOGITS
    Âł
    0.07
    0.06
     g
    0.06
     umb
    0.05
     Responsive
    0.05
    ÃŃ
    0.05
     trivial
    0.05
    opoly
    0.05
     rant
    0.05
     ho
    0.05
    Activations Density 0.000%

    No Known Activations