© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    elements related to personal connections and emotional depth

    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
     pur
    -0.06
    .truth
    -0.06
     Dip
    -0.06
     Gardner
    -0.06
     another
    -0.06
    avenport
    -0.05
     Pur
    -0.05
     Leg
    -0.05
    977
    -0.05
    arial
    -0.05
    POSITIVE LOGITS
     ours
    0.13
     hers
    0.10
     theirs
    0.10
    mine
    0.09
     yours
    0.09
     mine
    0.09
    ours
    0.08
    olla
    0.07
    inary
    0.07
     mines
    0.07
    Activations Density 0.026%

    No Known Activations