© 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. 106790
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs or structures

    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
    isor
    -0.08
    oise
    -0.07
    sut
    -0.07
    親
    -0.07
    ionic
    -0.07
    eut
    -0.06
    asta
    -0.06
    Ïĥμ
    -0.06
    mav
    -0.06
    sip
    -0.06
    POSITIVE LOGITS
    yal
    0.06
    Utc
    0.06
    getResource
    0.06
    ãĥªãĥ¼ãĤº
    0.06
     heck
    0.06
    Trader
    0.06
     craw
    0.06
     baÅŁÄ±nda
    0.05
     Binder
    0.05
    _SIG
    0.05
    Activations Density 0.000%

    No Known Activations