© 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. 73679
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structure and management

    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
    ê·¹
    -0.07
    edom
    -0.07
    aÅŁÄ±
    -0.06
    rey
    -0.06
    iamond
    -0.06
    tero
    -0.06
    venes
    -0.06
    reta
    -0.06
    yal
    -0.06
    åĨ
    -0.06
    POSITIVE LOGITS
    -wide
    0.08
    wide
    0.08
     wide
    0.07
    dna
    0.07
    Wide
    0.07
     DNA
    0.06
    -level
    0.06
    wand
    0.06
    ëĶ°
    0.06
     factors
    0.06
    Activations Density 0.008%

    No Known Activations