© 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. 83291
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Brother
    -0.07
    leet
    -0.07
     Detail
    -0.06
    åĥį
    -0.06
     Gig
    -0.06
    湿
    -0.06
     mates
    -0.06
     retir
    -0.06
    uld
    -0.06
    pos
    -0.06
    POSITIVE LOGITS
     equipments
    0.08
     saya
    0.08
     myself
    0.08
    alue
    0.07
    ç§ģãģ®
    0.07
    æĺŃ
    0.07
     my
    0.07
    SSION
    0.07
    æĪijçļĦ
    0.07
     mijn
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.