© 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. 105014
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and functions associated with alias handling and client operations

    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
    svc
    -0.07
    _UID
    -0.07
    antt
    -0.07
     queryInterface
    -0.07
    urette
    -0.07
    urdu
    -0.07
    амеÑĤ
    -0.07
    antium
    -0.07
    _Ptr
    -0.07
    LowerCase
    -0.07
    POSITIVE LOGITS
    NX
    0.08
     Steam
    0.07
     Miami
    0.06
     steam
    0.06
     pop
    0.06
     Redis
    0.06
     redis
    0.06
    esk
    0.06
    .Redis
    0.06
     Tre
    0.06
    Activations Density 0.032%

    No Known Activations