© 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. 15-LLAMASCOPE-RES-131K
    11. 26851
    Prev
    Next
    INDEX
    Explanations

    phrases that explore cultural differences and personal 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
    elper
    -0.08
    iani
    -0.07
    ément
    -0.07
    azzi
    -0.07
    ropic
    -0.06
     overrides
    -0.06
    alus
    -0.06
    rschein
    -0.06
    loy
    -0.06
    ç§Ģ
    -0.06
    POSITIVE LOGITS
     McDon
    0.07
    .scalablytyped
    0.06
    ØŃاد
    0.06
    FTA
    0.06
    دÙĪد
    0.06
     Ken
    0.06
     Goodman
    0.06
    Ł
    0.06
    ummer
    0.06
    shade
    0.06
    Activations Density 0.017%

    No Known Activations