© 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. 118327
    Prev
    Next
    INDEX
    Explanations

    words related to musical and lyrical elements

    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
     Blowjob
    -0.08
    ilar
    -0.08
    ãģĵãģĿ
    -0.07
    .Formatter
    -0.07
    pis
    -0.07
    =$('#
    -0.07
    ãģĮãģĬ
    -0.07
    orgen
    -0.07
    åĽ
    -0.07
    uri
    -0.07
    POSITIVE LOGITS
    ostel
    0.07
     magazine
    0.06
    Soft
    0.06
     festival
    0.06
    -esque
    0.06
     Rosenberg
    0.06
    dued
    0.05
     purported
    0.05
     hotel
    0.05
    -like
    0.05
    Activations Density 0.156%

    No Known Activations