© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77976
    Prev
    Next
    INDEX
    Explanations

    references to personal struggles and relationships within the context of a band or music scene

    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
    ngr
    -0.08
    ieber
    -0.07
    uzey
    -0.07
    uzzer
    -0.07
    autoload
    -0.07
    .Serve
    -0.07
    .IContainer
    -0.06
    ãĨ
    -0.06
    avid
    -0.06
    impse
    -0.06
    POSITIVE LOGITS
     alone
    0.10
     solo
    0.09
     Alone
    0.08
    alone
    0.08
     Solo
    0.07
     personally
    0.07
     twin
    0.06
     lead
    0.06
    esson
    0.06
    eso
    0.06
    Activations Density 0.039%

    No Known Activations