© 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. 108437
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technical specifications and manufacturing processes

    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
    ñana
    -0.07
    ugg
    -0.07
     
    -0.06
     equiv
    -0.06
    olla
    -0.06
    agher
    -0.06
    ---
    -0.06
    agi
    -0.06
    ahn
    -0.06
     Puzzle
    -0.06
    POSITIVE LOGITS
     SHALL
    0.10
     shall
    0.09
     Annex
    0.08
     Shall
    0.08
    shall
    0.07
    ohen
    0.07
    OKEN
    0.07
    ãĥĩãĥ«
    0.07
    ember
    0.07
    SessionFactory
    0.07
    Activations Density 0.002%

    No Known Activations