© 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. 38925
    Prev
    Next
    INDEX
    Explanations

    references to types and origins of precious materials, particularly pearls

    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
    antz
    -0.06
     Balk
    -0.06
    олоÑģ
    -0.06
    861
    -0.06
     soil
    -0.06
    arge
    -0.05
    unge
    -0.05
     اÙĨت
    -0.05
    湿
    -0.05
    erson
    -0.05
    POSITIVE LOGITS
     shells
    0.10
     shell
    0.09
     Pear
    0.09
    -shell
    0.08
    (shell
    0.08
    _shell
    0.08
    shell
    0.08
     pearl
    0.07
     Pearl
    0.07
     Shell
    0.07
    Activations Density 0.002%

    No Known Activations