© 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. 22-LLAMASCOPE-RES-131K
    11. 3689
    Prev
    Next
    INDEX
    Explanations

    instances of communication and scheduling details

    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
    amina
    -0.06
    eras
    -0.06
    kinson
    -0.06
     haut
    -0.06
     Months
    -0.06
    دÙĨ
    -0.06
    anio
    -0.06
    kie
    -0.06
    821
    -0.06
    inh
    -0.06
    POSITIVE LOGITS
     ETA
    0.11
     exact
    0.10
    ETA
    0.10
     arrival
    0.10
     approximate
    0.10
     Exact
    0.09
     estimated
    0.09
     Estimated
    0.09
    Expected
    0.08
    exact
    0.08
    Activations Density 0.009%

    No Known Activations