© 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. 84132
    Prev
    Next
    INDEX
    Explanations

    terms relating to water quality and contamination

    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
    é¼
    -0.07
    istra
    -0.07
    olia
    -0.06
    tps
    -0.06
     motion
    -0.06
     localhost
    -0.06
    ingroup
    -0.06
    alary
    -0.06
    menin
    -0.06
    Motion
    -0.06
    POSITIVE LOGITS
     Diss
    0.08
     Trace
    0.07
     Freund
    0.07
     trace
    0.07
     dissolved
    0.07
     Instrument
    0.07
     content
    0.06
     le
    0.06
    ảng
    0.06
     Meh
    0.06
    Activations Density 0.017%

    No Known Activations