© 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. 123972
    Prev
    Next
    INDEX
    Explanations

    references to standalone items or entities

    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
    weep
    -0.08
    ram
    -0.08
    lei
    -0.07
    lok
    -0.07
    /he
    -0.07
    reb
    -0.07
    iset
    -0.07
    lej
    -0.07
    echa
    -0.07
    inine
    -0.07
    POSITIVE LOGITS
    /single
    0.10
    quist
    0.07
     entity
    0.07
    å¼ı
    0.07
    vers
    0.07
    legate
    0.07
    gether
    0.06
     entities
    0.06
    llx
    0.06
     olarak
    0.06
    Activations Density 0.004%

    No Known Activations