© 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. 15-LLAMASCOPE-RES-131K
    11. 86682
    Prev
    Next
    INDEX
    Explanations

    references to colors and designs

    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
    åĬ¨çĶŁæĪIJ
    -0.07
    ijd
    -0.07
    conj
    -0.06
    ̧
    -0.06
    _VO
    -0.06
    procs
    -0.06
    UIL
    -0.06
    ERA
    -0.06
    ãĤ¤ãĥ³ãĥĪ
    -0.06
    ElementException
    -0.06
    POSITIVE LOGITS
     sizes
    0.11
     variety
    0.10
     varieties
    0.10
     varying
    0.10
     options
    0.09
     Sizes
    0.09
     range
    0.09
     available
    0.09
    sizes
    0.08
     ranges
    0.08
    Activations Density 0.123%

    No Known Activations