© 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 EvalsExportsinterp-engineNEWAPI 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. 97937
    Prev
    Next
    INDEX
    Explanations

    phrases indicating realizations or discoveries

    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
    å±¥
    -0.08
    iny
    -0.07
    -mf
    -0.07
    æŁ³
    -0.07
    Ãłnh
    -0.07
     trailers
    -0.07
    å¢ĥ
    -0.07
    _MM
    -0.07
    è«
    -0.07
    pector
    -0.07
    POSITIVE LOGITS
     Norm
    0.06
    enta
    0.06
    BLOCK
    0.06
     notice
    0.06
    owell
    0.06
    oxel
    0.06
    aaaaaaaa
    0.05
    825
    0.05
     format
    0.05
    imb
    0.05
    Activations Density 0.059%

    No Known Activations