© 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. 38961
    Prev
    Next
    INDEX
    Explanations

    references to personal feelings and relationships

    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
     somehow
    -0.06
     verdi
    -0.06
    ogui
    -0.06
    tog
    -0.06
    åĸ¶
    -0.06
    adesh
    -0.06
    adol
    -0.06
     somew
    -0.06
     already
    -0.06
    resolver
    -0.06
    POSITIVE LOGITS
     ever
    0.09
     anymore
    0.07
    stra
    0.06
    za
    0.06
     jamais
    0.06
    avatel
    0.06
    xFFFF
    0.06
    abyte
    0.06
    -ever
    0.06
    xFFFFFFFF
    0.06
    Activations Density 0.012%

    No Known Activations