© 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. 76551
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to performance metrics

    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
    odom
    -0.08
    vise
    -0.07
    iges
    -0.07
    rams
    -0.07
    odox
    -0.07
    "crypto
    -0.06
    _:*
    -0.06
    velle
    -0.06
    drv
    -0.06
    寺
    -0.06
    POSITIVE LOGITS
    ych
    0.06
    жд
    0.06
    wright
    0.06
    teenth
    0.06
    ickers
    0.06
    apl
    0.06
     altogether
    0.06
    над
    0.06
    reh
    0.06
    instances
    0.06
    Activations Density 0.012%

    No Known Activations