© 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. 17-LLAMASCOPE-RES-131K
    11. 39961
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript tags or components related to web development

    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
    edir
    -0.09
    aqu
    -0.08
    lify
    -0.08
    mae
    -0.08
    blr
    -0.08
    usu
    -0.07
    onu
    -0.07
    edith
    -0.07
    otti
    -0.07
    aan
    -0.07
    POSITIVE LOGITS
    urd
    0.06
    rank
    0.06
     pig
    0.06
    ORMAT
    0.05
     inde
    0.05
    ARED
    0.05
     Harm
    0.05
     supers
    0.05
    chos
    0.05
     v
    0.05
    Activations Density 0.001%

    No Known Activations