© 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. 107206
    Prev
    Next
    INDEX
    Explanations

    references to "work" and discussions about various types of professional or labor-related efforts

    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
    structor
    -0.06
    wf
    -0.06
    getto
    -0.06
    nore
    -0.06
     ones
    -0.06
    ts
    -0.05
    767
    -0.05
    crete
    -0.05
    endon
    -0.05
    bote
    -0.05
    POSITIVE LOGITS
     done
    0.10
    oldur
    0.09
    .scalablytyped
    0.09
     Done
    0.09
    Done
    0.08
    -done
    0.08
    done
    0.08
    .done
    0.08
     performed
    0.07
    @nate
    0.07
    Activations Density 0.024%

    No Known Activations