© 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. 105482
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating contribution to a report

    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
    obra
    -0.07
    getParameter
    -0.07
    ays
    -0.06
    EntryPoint
    -0.06
    amo
    -0.06
    ãĥ¬ãĥ¼
    -0.06
    uck
    -0.06
    .setCharacter
    -0.06
    _Impl
    -0.06
    263
    -0.06
    POSITIVE LOGITS
    etsk
    0.06
    anza
    0.06
    ersen
    0.06
    adro
    0.06
    ians
    0.06
    roph
    0.06
    á
    0.05
    zion
    0.05
    uD
    0.05
    åĶ
    0.05
    Activations Density 0.002%

    No Known Activations