© 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. 75401
    Prev
    Next
    INDEX
    Explanations

    mentions of radioactive waste management and public awareness

    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
    rahim
    -0.06
    duit
    -0.06
    thic
    -0.06
     vis
    -0.06
    ovement
    -0.05
    caffe
    -0.05
     linker
    -0.05
    fos
    -0.05
    unga
    -0.05
     mondo
    -0.05
    POSITIVE LOGITS
    redi
    0.08
    ikip
    0.07
    ibraries
    0.07
    (*)(
    0.07
     Mitar
    0.07
     chân
    0.07
    ilin
    0.07
    okino
    0.06
    iesen
    0.06
    -get
    0.06
    Activations Density 0.005%

    No Known Activations