© 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. 79904
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in the text

    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
    AsyncResult
    -0.09
    872
    -0.07
    ãĥ«ãĥĪ
    -0.06
    irket
    -0.06
    kyt
    -0.06
    beer
    -0.06
    ares
    -0.06
    MenuStrip
    -0.06
    رÙĬ
    -0.06
     ÐĴики
    -0.06
    POSITIVE LOGITS
    ocate
    0.07
    aná
    0.07
    ondon
    0.06
     Bray
    0.06
    vester
    0.06
    ox
    0.06
     Bea
    0.06
    nish
    0.06
    άνα
    0.06
    -addon
    0.06
    Activations Density 0.000%

    No Known Activations