© 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. 92138
    Prev
    Next
    INDEX
    Explanations

    verbs related to communication and information transfer

    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
    anga
    -0.06
    uell
    -0.06
    ynn
    -0.05
     normally
    -0.05
    108
    -0.05
     cross
    -0.05
    offee
    -0.05
     dames
    -0.05
     p
    -0.05
    ay
    -0.05
    POSITIVE LOGITS
     kepada
    0.09
    etine
    0.09
    ityEngine
    0.08
    elay
    0.08
    quam
    0.08
    .scalablytyped
    0.07
     unto
    0.07
    à¹Ħà¸Ľà¸¢
    0.07
    yntax
    0.07
    inel
    0.07
    Activations Density 0.024%

    No Known Activations