© 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. 27314
    Prev
    Next
    INDEX
    Explanations

    references to identity changes, particularly regarding names

    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
    Æł
    -0.08
    аÑİ
    -0.07
    emics
    -0.07
    recipient
    -0.07
     Beled
    -0.07
    ัà¸ĵà¸ij
    -0.07
    á»ijc
    -0.07
    Bindable
    -0.07
    isque
    -0.07
    gia
    -0.07
    POSITIVE LOGITS
     his
    0.06
     professional
    0.06
    enda
    0.06
    pd
    0.06
     Professional
    0.06
     Worm
    0.06
     childhood
    0.06
     career
    0.06
    539
    0.05
     رسÙħ
    0.05
    Activations Density 0.008%

    No Known Activations