© 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. 83088
    Prev
    Next
    INDEX
    Explanations

    instances of the StringBuilder class and its methods in code

    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
    ot
    -0.06
    ven
    -0.06
    729
    -0.06
    dan
    -0.06
     dist
    -0.05
     subject
    -0.05
     Brent
    -0.05
    eyer
    -0.05
    365
    -0.05
     plasma
    -0.05
    POSITIVE LOGITS
    à¥Įल
    0.08
    ¦æĥħ
    0.08
     append
    0.07
     Spy
    0.07
    FFE
    0.07
    SGlobal
    0.07
    itals
    0.07
    .append
    0.07
    bson
    0.07
    å¨
    0.07
    Activations Density 0.012%

    No Known Activations