© 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. 90107
    Prev
    Next
    INDEX
    Explanations

    references to animals and their treatment

    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
     Horton
    -0.07
    onda
    -0.07
     tanks
    -0.06
    pid
    -0.06
    rial
    -0.06
    èĥİ
    -0.06
    678
    -0.06
     tor
    -0.06
     Decomp
    -0.06
    çıŃ
    -0.06
    POSITIVE LOGITS
    enco
    0.09
    Owners
    0.08
     owners
    0.07
     bribery
    0.07
     muzzle
    0.07
     treats
    0.07
     Owners
    0.07
    enaire
    0.07
     owner
    0.06
     toy
    0.06
    Activations Density 0.093%

    No Known Activations