© 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. 125020
    Prev
    Next
    INDEX
    Explanations

    concepts related to the nature and types of relationships, particularly friendships and their dynamics

    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
    bÃŃr
    -0.06
    RTL
    -0.06
     treff
    -0.06
    /GPL
    -0.06
    beiten
    -0.06
    fasta
    -0.06
    .Ab
    -0.06
     Stap
    -0.06
    кова
    -0.06
     âĹij
    -0.06
    POSITIVE LOGITS
    uth
    0.07
     texts
    0.06
    icular
    0.06
     earliest
    0.06
     Hosp
    0.06
     textual
    0.06
    ored
    0.06
    ãĥį
    0.06
    '+↵
    0.06
    elist
    0.06
    Activations Density 0.001%

    No Known Activations