© 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 EvalsExportsAPI 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. 88698
    Prev
    Next
    INDEX
    Explanations

    package imports and library references in programming code, particularly related to Java and its frameworks

    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
    AuthGuard
    -0.06
    äre
    -0.06
    esin
    -0.06
    çĶº
    -0.06
    fragistics
    -0.06
    .RunWith
    -0.05
     Fax
    -0.05
    edii
    -0.05
    verture
    -0.05
    odi
    -0.05
    POSITIVE LOGITS
    .*;↵
    0.07
    ears
    0.07
     DefaultValue
    0.07
    اÙĬت
    0.07
    (PC
    0.07
     *\
    0.07
    .portal
    0.07
    ç¿Ķ
    0.07
    ấn
    0.07
    ENAME
    0.06
    Activations Density 0.017%

    No Known Activations