© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18068
    Prev
    Next
    INDEX
    Explanations

    phrases related to assistance or support in various 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
    irket
    -0.07
    arih
    -0.07
    antino
    -0.07
    ãĢĤ↵↵↵↵↵↵
    -0.07
    arResult
    -0.07
    ackbar
    -0.06
    rite
    -0.06
    rama
    -0.06
    å¾ħ
    -0.06
    _working
    -0.06
    POSITIVE LOGITS
     efforts
    0.08
     quests
    0.07
     understanding
    0.07
    iquid
    0.07
     task
    0.07
     quest
    0.07
    readcr
    0.07
    azen
    0.07
    LAB
    0.07
     understand
    0.07
    Activations Density 0.017%

    No Known Activations