© 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. 124776
    Prev
    Next
    INDEX
    Explanations

    code-related terminology within programming contexts

    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
     Hava
    -0.07
    .Sdk
    -0.07
    CompatActivity
    -0.07
    665
    -0.06
    ảnh
    -0.06
    .SDK
    -0.06
    769
    -0.06
    ActivityResult
    -0.06
    ÑĢой
    -0.06
     Emil
    -0.06
    POSITIVE LOGITS
    _CSR
    0.08
    \OptionsResolver
    0.07
    Symfony
    0.06
     Glo
    0.06
    EFA
    0.06
    APE
    0.06
     enctype
    0.06
     CSRF
    0.06
    елик
    0.06
     dna
    0.06
    Activations Density 0.005%

    No Known Activations