© 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. 60657
    Prev
    Next
    INDEX
    Explanations

    references to transportation and legal or financial assistance contexts

    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
    orest
    -0.08
    ги
    -0.07
    rens
    -0.07
    ÑĤÑı
    -0.07
    åIJIJ
    -0.07
    opsis
    -0.07
    ieber
    -0.06
     æ®
    -0.06
    istogram
    -0.06
    rschein
    -0.06
    POSITIVE LOGITS
     individual
    0.36
     Individual
    0.31
    individual
    0.30
    Individual
    0.29
     individuals
    0.25
    个人
    0.24
     personal
    0.24
    åĢĭ人
    0.24
     individ
    0.23
    _individual
    0.23
    Activations Density 0.137%

    No Known Activations