© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60406
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to control structures and error handling

    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
    edin
    -0.08
    iferay
    -0.08
    eft
    -0.07
    xec
    -0.07
    argo
    -0.07
    abyrin
    -0.07
    efs
    -0.07
    ÏĦικο
    -0.07
    Obsolete
    -0.07
    Äĥm
    -0.07
    POSITIVE LOGITS
    676
    0.06
    439
    0.06
    j
    0.06
    eres
    0.06
    374
    0.06
    /providers
    0.06
     Dol
    0.06
    679
    0.06
    739
    0.06
     if
    0.05
    Activations Density 0.032%

    No Known Activations