© 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. 27042
    Prev
    Next
    INDEX
    Explanations

    references to community organizations and initiatives focused on cultural exchange

    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
    AndGet
    -0.06
    ari
    -0.06
    OrDefault
    -0.06
    chers
    -0.06
    997
    -0.06
    998
    -0.06
     Constitutional
    -0.06
    uyu
    -0.06
    emie
    -0.06
    azes
    -0.06
    POSITIVE LOGITS
     extradition
    0.08
     extrad
    0.07
     recip
    0.07
    omid
    0.07
     Barbar
    0.07
     karÅŁ
    0.06
    ắm
    0.06
     exp
    0.06
    Rep
    0.06
    oka
    0.06
    Activations Density 0.159%

    No Known Activations