© 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. 77151
    Prev
    Next
    INDEX
    Explanations

    terms related to specific tools or resources, particularly in a business or management context

    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
    azen
    -0.07
    ambre
    -0.07
     Memorial
    -0.07
    itia
    -0.07
    encer
    -0.07
    é¹
    -0.07
    nan
    -0.06
    urret
    -0.06
    orget
    -0.06
    resi
    -0.06
    POSITIVE LOGITS
    ìľ¼ë¡ľ
    0.06
    ãĤ·ãĥ¼
    0.06
    lyn
    0.06
     à¤ķरà¤ķ
    0.06
     McMahon
    0.06
     nieu
    0.05
    ано
    0.05
    -buttons
    0.05
     Fatal
    0.05
    dar
    0.05
    Activations Density 0.002%

    No Known Activations