© 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. 127081
    Prev
    Next
    INDEX
    Explanations

    themes of love 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
    eyh
    -0.07
     treff
    -0.07
    CurrentValue
    -0.07
    anka
    -0.07
    alc
    -0.06
    icha
    -0.06
    orthand
    -0.06
    Advertisements
    -0.06
     bol
    -0.06
    .sessions
    -0.06
    POSITIVE LOGITS
    mma
    0.07
    iph
    0.06
    omp
    0.06
    peon
    0.06
    nite
    0.06
    олÑĮз
    0.06
    pNet
    0.06
    265
    0.06
    pires
    0.06
    Ĥæķ°
    0.05
    Activations Density 0.038%

    No Known Activations