© 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. 85810
    Prev
    Next
    INDEX
    Explanations

    elements related to conditional statements and error handling in 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
     Progressive
    -0.08
    assi
    -0.06
     progressive
    -0.06
    uzzi
    -0.06
     Conservative
    -0.06
     conservative
    -0.06
    eree
    -0.06
    ocs
    -0.06
     Blick
    -0.06
    legg
    -0.06
    POSITIVE LOGITS
     either
    0.17
    either
    0.15
     EITHER
    0.14
     Either
    0.14
    ither
    0.14
    Either
    0.14
     extremes
    0.13
    UpDown
    0.12
    InOut
    0.12
     Extreme
    0.11
    Activations Density 0.093%

    No Known Activations