© 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. 117499
    Prev
    Next
    INDEX
    Explanations

    technical terms and actions related to software configuration and usage

    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
    aire
    -0.07
    ellan
    -0.07
    regor
    -0.07
    avig
    -0.06
    etz
    -0.06
    acz
    -0.06
    eter
    -0.06
     bark
    -0.06
     implementation
    -0.06
    elan
    -0.06
    POSITIVE LOGITS
    RIA
    0.08
     SPDX
    0.07
    ãĥĪãĥ«
    0.06
    icense
    0.06
     Burke
    0.06
    APT
    0.06
     SPELL
    0.06
    Ñħодим
    0.06
     Spy
    0.06
     scaleFactor
    0.06
    Activations Density 0.001%

    No Known Activations