© 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. 16301
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to economic performance and corporate success

    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
     Redistributions
    -0.08
    obi
    -0.07
    dux
    -0.07
    edm
    -0.07
     kå
    -0.07
     vitam
    -0.07
     veter
    -0.07
    ноÑģÑĤей
    -0.07
    วà¸Ļ
    -0.06
    ysa
    -0.06
    POSITIVE LOGITS
    206
    0.06
     Cair
    0.06
    iral
    0.06
    205
    0.06
     opportunity
    0.06
    iffin
    0.06
     BIG
    0.06
     latter
    0.06
    Clip
    0.05
    atters
    0.05
    Activations Density 0.003%

    No Known Activations