© 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. 39162
    Prev
    Next
    INDEX
    Explanations

    financial figures 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
    dorf
    -0.07
    erox
    -0.07
    nder
    -0.07
    hurst
    -0.06
    'options
    -0.06
    TRS
    -0.06
    anyl
    -0.06
    nv
    -0.06
     Ny
    -0.06
    odyn
    -0.06
    POSITIVE LOGITS
    MOTE
    0.07
     Heller
    0.07
    essian
    0.06
    164
    0.06
     Serg
    0.06
    ika
    0.06
    ynes
    0.06
    λοÏĤ
    0.06
    tep
    0.06
    Ñıб
    0.06
    Activations Density 0.015%

    No Known Activations