© 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. 57787
    Prev
    Next
    INDEX
    Explanations

    references to job roles and responsibilities

    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
    ixin
    -0.07
    dum
    -0.07
    ANTLR
    -0.06
    unker
    -0.06
    ="../../../
    -0.06
    uta
    -0.06
    zen
    -0.06
    arden
    -0.06
    hsi
    -0.06
    angu
    -0.06
    POSITIVE LOGITS
     grounds
    0.08
     assist
    0.07
     admin
    0.07
     administration
    0.07
     miscellaneous
    0.07
     administrative
    0.06
    .obtain
    0.06
    leh
    0.06
     administrations
    0.06
     merch
    0.06
    Activations Density 0.060%

    No Known Activations