© 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. 93094
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific expressions and notations

    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
    amma
    -0.08
    edir
    -0.08
    RIPT
    -0.08
    adden
    -0.07
    dds
    -0.07
    onse
    -0.07
     esac
    -0.07
    edl
    -0.07
    üf
    -0.07
    onet
    -0.07
    POSITIVE LOGITS
     اÙĦÙħص
    0.06
     Banking
    0.06
     лиÑĩ
    0.05
     sept
    0.05
     ввод
    0.05
     Objects
    0.05
     carr
    0.05
     tempt
    0.05
    term
    0.05
    utin
    0.05
    Activations Density 0.241%

    No Known Activations