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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103543
    Prev
    Next
    INDEX
    Explanations

    measurements and specifications related to product dimensions

    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
    iku
    -0.07
    ibold
    -0.07
    pNet
    -0.07
    osl
    -0.07
    asto
    -0.07
    å»
    -0.07
    876
    -0.07
    sworth
    -0.06
    034
    -0.06
    ANDOM
    -0.06
    POSITIVE LOGITS
     /
    0.06
    apur
    0.06
    cher
    0.06
    ãĥĶãĥ¼
    0.06
    PIP
    0.06
    getattr
    0.05
     hava
    0.05
    æķ¦
    0.05
     Ges
    0.05
     kun
    0.05
    Activations Density 0.004%

    No Known Activations