© 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. 9-LLAMASCOPE-RES-131K
    11. 95828
    Prev
    Next
    INDEX
    Explanations

    expressions of personal transformation and resilience in challenging circumstances

    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
    igel
    -0.07
    iggs
    -0.06
    abh
    -0.06
    ello
    -0.06
    ovsky
    -0.06
    вад
    -0.06
    rep
    -0.06
    utsch
    -0.06
    stial
    -0.06
    igure
    -0.06
    POSITIVE LOGITS
    noÅĽÄĩ
    0.07
    dag
    0.06
     -*-č↵
    0.06
     жизни
    0.06
    esz
    0.06
    ateur
    0.06
    Vendor
    0.06
    .tip
    0.06
    oggled
    0.06
     expectancy
    0.06
    Activations Density 0.049%

    No Known Activations