© 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. 79249
    Prev
    Next
    INDEX
    Explanations

    phrases related to administrative or procedural tasks

    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
    awah
    -0.08
    regor
    -0.07
    Ñĵ
    -0.07
     finally
    -0.07
     prec
    -0.06
    apore
    -0.06
    anship
    -0.06
    .CopyTo
    -0.06
     Prep
    -0.06
     dÄ±ÅŁÄ±
    -0.06
    POSITIVE LOGITS
     immediate
    0.20
     immediately
    0.20
     immedi
    0.16
     Immediate
    0.14
     Immediately
    0.14
     after
    0.13
     soon
    0.13
     sofort
    0.12
     shortly
    0.12
    Immediate
    0.11
    Activations Density 0.101%

    No Known Activations