© 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. 17-LLAMASCOPE-RES-131K
    11. 54398
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate and technological changes

    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
    .scalablytyped
    -0.09
    ngo
    -0.08
    ihan
    -0.07
    .toolbox
    -0.07
    inals
    -0.07
    rike
    -0.07
     HACK
    -0.07
    (çģ«
    -0.07
    rvé
    -0.07
    polator
    -0.07
    POSITIVE LOGITS
     Soviet
    0.07
    oner
    0.06
     erst
    0.06
    ê
    0.06
     once
    0.06
    orate
    0.06
     доÑĤ
    0.06
     imb
    0.05
     Former
    0.05
     former
    0.05
    Activations Density 0.348%

    No Known Activations