© 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. 95791
    Prev
    Next
    INDEX
    Explanations

    references to nominations and the nomination process

    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
    ey
    -0.07
    entine
    -0.06
    iras
    -0.06
    irate
    -0.06
    eki
    -0.06
    kek
    -0.06
    uhl
    -0.06
    omm
    -0.06
    unto
    -0.06
    evi
    -0.06
    POSITIVE LOGITS
    lıģına
    0.07
    isman
    0.06
    getSingleton
    0.06
    åIJĪãĤıãģĽ
    0.06
    regor
    0.06
    ären
    0.06
    ÑĮогод
    0.06
    IDAD
    0.06
    rust
    0.06
    lıģının
    0.06
    Activations Density 0.003%

    No Known Activations