© 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. 117637
    Prev
    Next
    INDEX
    Explanations

    language indicating the need for precise communication in critical situations

    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
     ↵↵
    -0.07
     å¹
    -0.07
    /Instruction
    -0.07
     огÑĢа
    -0.06
    jak
    -0.06
     Drake
    -0.06
     lcm
    -0.06
     Berry
    -0.06
     distributed
    -0.06
    distributed
    -0.06
    POSITIVE LOGITS
     submit
    0.10
     submitting
    0.09
    submit
    0.09
     supplying
    0.08
     submits
    0.08
    supply
    0.08
    Supply
    0.07
     ìłľì¶ľ
    0.07
     submitted
    0.07
     tell
    0.07
    Activations Density 0.041%

    No Known Activations