© 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. 78800
    Prev
    Next
    INDEX
    Explanations

    references to the 'this' keyword and context-related keywords in programming or markup languages

    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
    asket
    -0.08
    mah
    -0.07
    Äįek
    -0.07
    moid
    -0.07
    ntl
    -0.06
     luggage
    -0.06
    wnd
    -0.06
    опол
    -0.06
    loomberg
    -0.06
    ÑĪÑĮ
    -0.06
    POSITIVE LOGITS
    atre
    0.08
    ero
    0.06
    ches
    0.06
    ERO
    0.06
    utom
    0.06
     Vend
    0.06
    ав
    0.05
    559
    0.05
    ADE
    0.05
     Wander
    0.05
    Activations Density 0.001%

    No Known Activations