© 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. 80474
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and names

    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
    asca
    -0.07
    ocument
    -0.07
    rise
    -0.07
    ayas
    -0.07
    tout
    -0.07
    ufen
    -0.07
    meyen
    -0.07
    ctype
    -0.07
    pais
    -0.07
    ayd
    -0.06
    POSITIVE LOGITS
    TestFixture
    0.06
    ader
    0.06
    Nib
    0.06
    lingen
    0.06
    TL
    0.06
    okol
    0.06
    tl
    0.06
    åħĥ
    0.06
    ekk
    0.06
     Hardcover
    0.06
    Activations Density 0.009%

    No Known Activations