© 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. 73735
    Prev
    Next
    INDEX
    Explanations

    programming and mathematical syntax related to data processing and analysis

    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
     Achilles
    -0.07
    Spi
    -0.07
    963
    -0.07
    IfExists
    -0.06
    faction
    -0.06
    duit
    -0.06
    _Abstract
    -0.06
    ADE
    -0.06
    mai
    -0.06
     mitt
    -0.06
    POSITIVE LOGITS
    jezd
    0.07
    ">//
    0.07
    .SwingConstants
    0.06
    coe
    0.06
    orer
    0.06
    ã
    0.06
    untu
    0.06
    dorf
    0.06
    _vlan
    0.06
    "":
    0.06
    Activations Density 0.083%

    No Known Activations