© 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. 14828
    Prev
    Next
    INDEX
    Explanations

    financial metrics and related terms

    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
    zure
    -0.08
     à¤ķहन
    -0.07
    еÑĢап
    -0.07
    upo
    -0.07
    ugin
    -0.07
    .ci
    -0.07
    buz
    -0.07
    prenom
    -0.07
    plode
    -0.07
     ıs
    -0.07
    POSITIVE LOGITS
    11
    0.07
    ix
    0.07
    111
    0.07
    12
    0.07
    ilter
    0.06
    13
    0.06
    138
    0.06
     Condition
    0.06
    xi
    0.06
     saison
    0.06
    Activations Density 0.010%

    No Known Activations