© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29150
    Prev
    Next
    INDEX
    Explanations

    descriptions of gameplay mechanics and 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
    æŃ©
    -0.07
    iya
    -0.06
    illus
    -0.06
    akt
    -0.06
    echan
    -0.06
    rug
    -0.06
     walks
    -0.06
    jour
    -0.06
    quate
    -0.05
    ano
    -0.05
    POSITIVE LOGITS
     race
    0.07
    ลา
    0.07
     chic
    0.07
     track
    0.07
     Lem
    0.07
    пов
    0.07
     Asphalt
    0.07
     car
    0.07
     lÃłn
    0.07
     speed
    0.07
    Activations Density 0.020%

    No Known Activations