© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127219
    Prev
    Next
    INDEX
    Explanations

    references to emotional struggles and overwhelming 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
     either
    -0.06
     Trot
    -0.06
    ulado
    -0.06
    /
    -0.06
     or
    -0.06
     BJ
    -0.05
    ining
    -0.05
    áºŃm
    -0.05
    ://
    -0.05
    uito
    -0.05
    POSITIVE LOGITS
    uhn
    0.08
    VERTISE
    0.08
    ANI
    0.08
    erif
    0.08
    ecta
    0.07
    ÏĥÏį
    0.07
    egal
    0.07
     Tib
    0.07
    Hover
    0.07
    acci
    0.07
    Activations Density 0.008%

    No Known Activations