© 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. 17-LLAMASCOPE-RES-131K
    11. 126569
    Prev
    Next
    INDEX
    Explanations

    references to sensory experiences and engagement

    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
    wy
    -0.07
    ardy
    -0.07
    iek
    -0.07
    aming
    -0.07
    oppel
    -0.06
    emey
    -0.06
     Beam
    -0.06
    minster
    -0.06
    eton
    -0.06
     macros
    -0.06
    POSITIVE LOGITS
    /color
    0.09
    ONS
    0.08
    è¦ļ
    0.07
    FUL
    0.07
    webtoken
    0.07
    Unchecked
    0.07
    /em
    0.07
    anchors
    0.07
    .IContainer
    0.07
     pall
    0.07
    Activations Density 0.012%

    No Known Activations