© 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. 2217
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to communication and instruction

    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
     whe
    -0.06
     transparent
    -0.06
    usk
    -0.06
    aci
    -0.06
    ETCH
    -0.06
    üst
    -0.06
     Amb
    -0.05
    elian
    -0.05
    urgy
    -0.05
     u
    -0.05
    POSITIVE LOGITS
    ãĤ¹ãĥ¬
    0.07
    ioni
    0.07
    ucene
    0.07
    okane
    0.07
    427
    0.07
    äch
    0.07
    Shar
    0.06
    ivre
    0.06
     Fors
    0.06
    iquer
    0.06
    Activations Density 0.000%

    No Known Activations