© 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. 106091
    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
    еÑĩ
    -0.08
    ùa
    -0.08
     godt
    -0.08
    ÙĤاÙĦ
    -0.07
    seau
    -0.07
     взаим
    -0.07
     воÑĤ
    -0.07
     homosex
    -0.07
    ientes
    -0.07
    нÑıÑĤи
    -0.07
    POSITIVE LOGITS
    Å
    0.07
    erville
    0.06
    È
    0.05
    chas
    0.05
    utch
    0.05
     grade
    0.05
    pus
    0.05
     Bruce
    0.05
     Dict
    0.05
     rid
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.