© 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. 72228
    Prev
    Next
    INDEX
    Explanations

    instances of code or programming terminologies

    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
    emple
    -0.07
    iddi
    -0.07
    acre
    -0.07
     anzeigen
    -0.07
    acet
    -0.06
    appen
    -0.06
    ancock
    -0.06
    åľĪ
    -0.06
    atos
    -0.06
     elementType
    -0.06
    POSITIVE LOGITS
    NDER
    0.06
    onet
    0.06
     exact
    0.06
    ÃŃrk
    0.06
    andel
    0.06
    ियत
    0.06
    sonian
    0.06
    exact
    0.06
    mint
    0.06
    packed
    0.06
    Activations Density 0.061%

    No Known Activations