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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74528
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and ease of various processes

    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
    że
    -0.07
     Enough
    -0.07
    argo
    -0.06
     unfit
    -0.06
    to
    -0.06
    fusion
    -0.06
     STRICT
    -0.06
     myself
    -0.06
     Harding
    -0.05
    bij
    -0.05
    POSITIVE LOGITS
     easier
    0.10
     ease
    0.10
     Ease
    0.08
     easy
    0.08
     easiest
    0.07
    سÙĩ
    0.07
     dá»ħ
    0.07
    elier
    0.07
    Ease
    0.07
     à¤Ĩस
    0.07
    Activations Density 0.016%

    No Known Activations