© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95211
    Prev
    Next
    INDEX
    Explanations

    data about measurements or specifications

    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
    quisite
    -0.07
    arian
    -0.06
    ani
    -0.06
    quisites
    -0.06
    oi
    -0.06
    ãģŁãģĹ
    -0.06
    åł´æīĢ
    -0.06
    ле
    -0.06
    teil
    -0.06
    -tip
    -0.06
    POSITIVE LOGITS
    vem
    0.07
    722
    0.07
    512
    0.07
    772
    0.06
    se
    0.06
    utto
    0.06
    ÏĦαν
    0.06
    ko
    0.06
    ayet
    0.06
    erval
    0.06
    Activations Density 0.001%

    No Known Activations