© 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. 96915
    Prev
    Next
    INDEX
    Explanations

    elements related to color themes and design options for applications

    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
    porte
    -0.06
    ools
    -0.06
     Psy
    -0.06
    zv
    -0.06
    etch
    -0.06
     Gardner
    -0.06
     Dynamo
    -0.06
    tsky
    -0.06
    .za
    -0.05
     Sole
    -0.05
    POSITIVE LOGITS
    .effects
    0.07
    URATION
    0.07
     ÑģоÑģ
    0.07
    igu
    0.07
    lrt
    0.07
    LETE
    0.06
    ãģķãĤī
    0.06
    aÄį
    0.06
     withd
    0.06
    éĹ
    0.06
    Activations Density 0.023%

    No Known Activations