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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76999
    Prev
    Next
    INDEX
    Explanations

    programming-related functionality and error handling in 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
    atz
    -0.10
    urd
    -0.07
    té
    -0.07
    ÙĴس
    -0.07
    TexCoord
    -0.07
     SEARCH
    -0.07
    elden
    -0.07
    रण
    -0.07
    utherland
    -0.07
     CHARSET
    -0.07
    POSITIVE LOGITS
     confirmation
    0.10
     confirm
    0.10
     Confirm
    0.09
     yes
    0.09
     Yes
    0.09
     decision
    0.09
    .confirm
    0.09
     consent
    0.09
     confirms
    0.08
     acceptance
    0.08
    Activations Density 0.020%

    No Known Activations