© 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. 16253
    Prev
    Next
    INDEX
    Explanations

    phrases related to waste management and cleaning services

    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
    Lexer
    -0.06
    apt
    -0.06
    olo
    -0.06
    ilig
    -0.06
    neutral
    -0.06
     fl
    -0.06
    achu
    -0.06
    agar
    -0.06
    ams
    -0.06
     neutral
    -0.06
    POSITIVE LOGITS
     alike
    0.12
    REA
    0.08
     respectively
    0.07
     Intr
    0.07
     respective
    0.07
    elerik
    0.07
    lesia
    0.07
     Feinstein
    0.06
    ectar
    0.06
    ibilit
    0.06
    Activations Density 0.121%

    No Known Activations