© 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 EvalsExportsAPI 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. 78535
    Prev
    Next
    INDEX
    Explanations

    significant events or conferences in academic contexts

    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
    rieve
    -0.07
    NDER
    -0.06
    achment
    -0.06
    ظ
    -0.06
     TODO
    -0.06
    cko
    -0.06
    elper
    -0.06
    ibal
    -0.06
    kers
    -0.06
    orthand
    -0.06
    POSITIVE LOGITS
     Springer
    0.08
    åºľ
    0.08
     proceedings
    0.07
    /INFO
    0.07
     Gent
    0.07
    .press
    0.06
     confiscated
    0.06
     Lange
    0.06
    tlement
    0.06
    yas
    0.06
    Activations Density 0.003%

    No Known Activations