© 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. 5-LLAMASCOPE-RES-131K
    11. 126581
    Prev
    Next
    INDEX
    Explanations

    programming-related null values and boolean operations

    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
    SingleNode
    -0.07
    ycler
    -0.07
    erville
    -0.07
    æķ·
    -0.07
    iswa
    -0.07
    .converter
    -0.06
    ÙĪÛĮزÛĮ
    -0.06
    леж
    -0.06
    uste
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
    ero
    0.07
    ptime
    0.06
    ERO
    0.06
    503
    0.06
    ensch
    0.06
    ieron
    0.06
     rec
    0.06
    anj
    0.06
    áce
    0.06
    agram
    0.06
    Activations Density 0.033%

    No Known Activations