© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95629
    Prev
    Next
    INDEX
    Explanations

    specific programming language syntax elements and mathematical notations

    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
    anne
    -0.08
    ippet
    -0.08
    appa
    -0.07
    ergency
    -0.07
    mpar
    -0.07
    WARE
    -0.07
     Unsure
    -0.07
    teri
    -0.07
    omers
    -0.07
    ARSER
    -0.07
    POSITIVE LOGITS
    afen
    0.07
    idal
    0.07
     dro
    0.06
    esson
    0.06
     Cr
    0.06
    aje
    0.06
     Dro
    0.06
    ãĤ¤ãĤ¯
    0.06
     Rule
    0.06
    omic
    0.06
    Activations Density 0.001%

    No Known Activations