© 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. 120864
    Prev
    Next
    INDEX
    Explanations

    references to the United States

    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
    ModelProperty
    -0.08
    usercontent
    -0.08
    achusetts
    -0.07
    dez
    -0.06
    early
    -0.06
    üstü
    -0.06
    ean
    -0.06
    akk
    -0.06
    ohn
    -0.06
    apg
    -0.06
    POSITIVE LOGITS
    521
    0.08
    odom
    0.07
    bject
    0.07
    áy
    0.07
    ableObject
    0.06
    opup
    0.06
    so
    0.06
    аÑĤкÑĥ
    0.06
     è©
    0.06
    itz
    0.06
    Activations Density 0.024%

    No Known Activations