© 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. 17940
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and emotional experiences

    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
    entai
    -0.07
    hti
    -0.07
    outine
    -0.07
    ownik
    -0.07
    ront
    -0.07
    Äıte
    -0.07
    аÑĤо
    -0.06
    .Invalid
    -0.06
    obe
    -0.06
     ìŬ룬ë¶Ħ
    -0.06
    POSITIVE LOGITS
     nackte
    0.07
    nw
    0.07
    hoe
    0.06
     since
    0.06
    hle
    0.06
     tissue
    0.06
     ard
    0.05
     afar
    0.05
     Relationships
    0.05
    indr
    0.05
    Activations Density 0.002%

    No Known Activations