© 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 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. 3488
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to tasks or activities that require significant time and effort

    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
    važ
    -0.08
    ¶Į
    -0.08
    žÃŃ
    -0.08
    ucher
    -0.08
    /her
    -0.08
    žel
    -0.07
    laÅŁ
    -0.07
    geç
    -0.07
    lesen
    -0.07
    úa
    -0.07
    POSITIVE LOGITS
    acht
    0.07
    çIJ
    0.06
    liness
    0.06
    evity
    0.06
    idot
    0.06
    /time
    0.06
     Vance
    0.06
    éĺħ
    0.06
    OURS
    0.06
    erals
    0.06
    Activations Density 0.007%

    No Known Activations