© 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. 9-LLAMASCOPE-RES-131K
    11. 98768
    Prev
    Next
    INDEX
    Explanations

    numerical data or values related to parameters and statistics

    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
     nors
    -0.06
    ourg
    -0.06
     Props
    -0.06
     nad
    -0.06
    æ²¢
    -0.06
    .sess
    -0.05
    ish
    -0.05
    ivan
    -0.05
     Hercules
    -0.05
    _TRANSFORM
    -0.05
    POSITIVE LOGITS
    esto
    0.08
    emek
    0.07
    Fel
    0.07
    odos
    0.07
    ayd
    0.07
    ipa
    0.07
    enville
    0.07
    emoc
    0.07
     Giang
    0.07
    kee
    0.07
    Activations Density 0.001%

    No Known Activations