© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28955
    Prev
    Next
    INDEX
    Explanations

    mentions of academic and professional qualifications or 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
    StackNavigator
    -0.07
    ÏĨή
    -0.07
    owo
    -0.07
    olla
    -0.06
    .dds
    -0.06
    аÑĤов
    -0.06
    zag
    -0.06
    _Tis
    -0.06
    aģı
    -0.06
    TM
    -0.06
    POSITIVE LOGITS
     marc
    0.07
    ux
    0.06
    avr
    0.06
    ,
    0.06
    год
    0.06
    mapped
    0.06
    rary
    0.06
     boot
    0.06
    isting
    0.06
    igue
    0.06
    Activations Density 0.003%

    No Known Activations