© 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. 39656
    Prev
    Next
    INDEX
    Explanations

    expressions of complex emotional experiences and interpersonal 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
     Moo
    -0.07
    rror
    -0.06
    omik
    -0.06
    riad
    -0.06
     hostages
    -0.06
    hetto
    -0.06
    vrd
    -0.06
    Syntax
    -0.05
     sending
    -0.05
    riott
    -0.05
    POSITIVE LOGITS
    被
    0.11
    åıĹåĪ°
    0.10
     receiving
    0.10
    being
    0.10
     被
    0.09
     recibir
    0.09
    Receive
    0.09
     being
    0.09
     Receive
    0.09
     receive
    0.09
    Activations Density 0.071%

    No Known Activations