Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128797
    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
    elden
    -0.08
    ansa
    -0.07
    porte
    -0.07
    mtx
    -0.07
    ongan
    -0.07
    à¥Īर
    -0.07
    egl
    -0.06
    客
    -0.06
     decades
    -0.06
    lyn
    -0.06
    POSITIVE LOGITS
     ì¢ĭìķĦ
    0.07
    ZY
    0.07
     bás
    0.07
    çĶ
    0.06
    elage
    0.06
    .Listener
    0.06
    allis
    0.06
    .ContentType
    0.06
    asz
    0.06
     mog
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.