© 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. 9-LLAMASCOPE-RES-131K
    11. 97253
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to modeling and design in systems or networks

    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
     oily
    -0.06
    omy
    -0.06
    USB
    -0.06
    SystemService
    -0.06
     Tem
    -0.06
     unheard
    -0.06
    berger
    -0.05
    tt
    -0.05
    illator
    -0.05
    hait
    -0.05
    POSITIVE LOGITS
    âĹİ
    0.08
    imiter
    0.07
    ¥IJ
    0.07
    igram
    0.07
    ogui
    0.07
     ëį¤íĶĦ
    0.07
    (çģ«
    0.07
    ESCO
    0.07
    aley
    0.07
    igli
    0.07
    Activations Density 0.001%

    No Known Activations