© 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. 93990
    Prev
    Next
    INDEX
    Explanations

    phrases related to career development and learning opportunities

    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
    ihan
    -0.07
    Traversal
    -0.07
    BUF
    -0.06
    алÑİ
    -0.06
    èŃľ
    -0.06
    æĵļ
    -0.06
    orf
    -0.06
    _WM
    -0.06
    .Names
    -0.06
    ë¡Ģ
    -0.06
    POSITIVE LOGITS
    ewood
    0.07
     certain
    0.06
    oli
    0.06
     abol
    0.06
     masses
    0.06
     Both
    0.06
    inos
    0.06
    chner
    0.06
    ives
    0.06
     rest
    0.06
    Activations Density 0.179%

    No Known Activations