© 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. 40896
    Prev
    Next
    INDEX
    Explanations

    emotional experiences and reflections on events

    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
    Å¡it
    -0.06
    781
    -0.06
    IVEN
    -0.06
    uchen
    -0.06
     hasn
    -0.06
     çĽ
    -0.05
    urgent
    -0.05
     imz
    -0.05
    ICA
    -0.05
    ACHI
    -0.05
    POSITIVE LOGITS
     mine
    0.09
     ours
    0.08
    _was
    0.07
    tÃŃ
    0.07
    etz
    0.07
     was
    0.07
    ours
    0.07
     liá»ģn
    0.07
    was
    0.07
    mine
    0.07
    Activations Density 0.322%

    No Known Activations