© 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. 41761
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental health and its influence on creativity

    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
    ÙĤÛĮ
    -0.08
    .tk
    -0.08
    arat
    -0.07
    totals
    -0.07
    -tm
    -0.07
     ancor
    -0.07
    ษ
    -0.07
    perator
    -0.07
    _FACE
    -0.07
     výj
    -0.07
    POSITIVE LOGITS
     itself
    0.07
     indirectly
    0.06
     pot
    0.06
     prime
    0.06
    erver
    0.06
     directly
    0.06
     partly
    0.06
    riday
    0.06
     related
    0.06
     incident
    0.06
    Activations Density 0.055%

    No Known Activations