© 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. 15-LLAMASCOPE-RES-131K
    11. 62345
    Prev
    Next
    INDEX
    Explanations

    references to harsh living conditions or survival experiences

    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
    ymmetric
    -0.07
    SYM
    -0.07
    zzo
    -0.07
    etak
    -0.07
    ecute
    -0.07
    Ymd
    -0.07
    .heroku
    -0.07
    ynchronously
    -0.07
    etto
    -0.07
    æŃ³
    -0.07
    POSITIVE LOGITS
     morale
    0.08
     unofficial
    0.07
     personal
    0.07
     married
    0.07
     Lime
    0.07
     union
    0.07
     leave
    0.06
     night
    0.06
     whistleblower
    0.06
    locker
    0.06
    Activations Density 0.182%

    No Known Activations