© 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 EvalsExportsinterp-engineNEWAPI 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. 117387
    Prev
    Next
    INDEX
    Explanations

    aspects of character development and emotional responses

    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
     recent
    -0.06
    _cores
    -0.06
     years
    -0.06
    aight
    -0.06
    pletely
    -0.06
    _recent
    -0.06
     Jahre
    -0.06
    ennes
    -0.06
     Kick
    -0.05
    ìł¸
    -0.05
    POSITIVE LOGITS
     throughout
    0.18
     occasionally
    0.15
     Throughout
    0.15
    Throughout
    0.15
     whenever
    0.13
     occasional
    0.13
     sometimes
    0.13
     frequently
    0.12
     Occasionally
    0.11
    sometimes
    0.11
    Activations Density 0.230%

    No Known Activations