© 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 EvalsExportsAPI 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. 57311
    Prev
    Next
    INDEX
    Explanations

    expressions of conflict or negative feelings towards others and situations

    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
    ฤ
    -0.07
    éis
    -0.07
     Honor
    -0.07
    ãn
    -0.07
    Å©ng
    -0.07
    .attachment
    -0.07
    cision
    -0.07
    uintptr
    -0.06
    ebo
    -0.06
    ysa
    -0.06
    POSITIVE LOGITS
     prayers
    0.08
     prayed
    0.07
     pray
    0.07
     rel
    0.07
     victory
    0.06
     prayer
    0.06
     wishing
    0.06
     relief
    0.06
     hopes
    0.06
     nem
    0.06
    Activations Density 0.050%

    No Known Activations