© 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. 72368
    Prev
    Next
    INDEX
    Explanations

    sections or conclusions in a scientific document

    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
    using
    -0.07
    .Assertions
    -0.06
    obo
    -0.06
    hev
    -0.06
    CLUDING
    -0.06
    ÏĥÏĦÏģο
    -0.06
    es
    -0.06
    ulos
    -0.06
    ucci
    -0.06
    iode
    -0.06
    POSITIVE LOGITS
    ingles
    0.07
    iesel
    0.07
    emain
    0.06
    ãĥ³ãĥĦ
    0.06
    illions
    0.06
    íĦ
    0.06
    uitka
    0.06
    classname
    0.06
    acr
    0.06
    Äįin
    0.06
    Activations Density 0.030%

    No Known Activations