© 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. 5529
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and legal compliance

    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
    anax
    -0.07
    icked
    -0.07
    bourg
    -0.07
    ÙĪÙĨÛĮ
    -0.06
    ords
    -0.06
    pus
    -0.06
     Guth
    -0.06
     zach
    -0.06
    اØŃÛĮ
    -0.06
    inges
    -0.06
    POSITIVE LOGITS
     Hak
    0.06
     Spinner
    0.06
    æĥħ
    0.06
    SenderId
    0.06
    837
    0.06
     Lic
    0.06
    elm
    0.06
    \Blueprint
    0.06
    airport
    0.06
    ivel
    0.06
    Activations Density 0.003%

    No Known Activations