© 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. 9-LLAMASCOPE-RES-131K
    11. 96307
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate expectations and responsibilities in a mentorship context

    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
    okoj
    -0.09
    ije
    -0.08
    oldem
    -0.08
    enou
    -0.08
    educt
    -0.07
    ivol
    -0.07
    Leaks
    -0.07
    akk
    -0.07
    алеж
    -0.07
    LOSS
    -0.07
    POSITIVE LOGITS
     mean
    0.06
     Anders
    0.05
     Cumberland
    0.05
     sensitive
    0.05
     perfectly
    0.05
     Grove
    0.05
     Hend
    0.05
     cul
    0.05
    rove
    0.05
    adians
    0.05
    Activations Density 0.026%

    No Known Activations