© 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. 17-LLAMASCOPE-RES-131K
    11. 56307
    Prev
    Next
    INDEX
    Explanations

    CSS styles and layout properties

    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
    ayd
    -0.08
    ibaba
    -0.07
    olare
    -0.07
    nave
    -0.06
    oload
    -0.06
    ionale
    -0.06
    yssey
    -0.06
    Ãłng
    -0.06
    phant
    -0.06
     вов
    -0.06
    POSITIVE LOGITS
     Hem
    0.07
    abb
    0.06
     Programmer
    0.06
    arge
    0.06
    hem
    0.06
     Great
    0.06
    rem
    0.06
     hem
    0.06
    igham
    0.06
    mate
    0.06
    Activations Density 0.010%

    No Known Activations