© 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. 120755
    Prev
    Next
    INDEX
    Explanations

    conditional statements and logical checks within 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
    ivec
    -0.08
    ónico
    -0.07
    вами
    -0.07
    Ù¾ÛĮ
    -0.07
    -cols
    -0.07
    еÑĢалÑĮ
    -0.07
    /******/
    -0.07
    agenta
    -0.07
    Ø´Ùĩ
    -0.07
    stras
    -0.07
    POSITIVE LOGITS
     assertNotNull
    0.08
     null
    0.07
     if
    0.07
    NullOrEmpty
    0.07
     Null
    0.07
    raith
    0.07
    .IsNullOrEmpty
    0.07
     Empty
    0.07
    .notNull
    0.07
    if
    0.06
    Activations Density 0.069%

    No Known Activations