© 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. 27480
    Prev
    Next
    INDEX
    Explanations

    instances of complex interpersonal relationships and emotional turmoil

    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
    raphics
    -0.08
    ReadStream
    -0.08
    .synthetic
    -0.08
    ordion
    -0.08
    .Raise
    -0.08
    eful
    -0.08
    jab
    -0.07
    afx
    -0.07
    laughter
    -0.07
    åĪļæīį
    -0.07
    POSITIVE LOGITS
     soon
    0.10
     becomes
    0.08
     discover
    0.08
     discovers
    0.08
     Soon
    0.07
     learns
    0.07
     become
    0.07
     learn
    0.06
     torn
    0.06
     begins
    0.06
    Activations Density 0.030%

    No Known Activations