© 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. 84113
    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
    åIJ§
    -0.07
    comb
    -0.06
     .
    -0.06
     rem
    -0.06
     int
    -0.06
     comb
    -0.06
     Butler
    -0.06
    chner
    -0.05
     Common
    -0.05
     al
    -0.05
    POSITIVE LOGITS
    IFn
    0.09
     möglich
    0.08
    å°½
    0.08
    DCALL
    0.08
    otel
    0.08
     istiyorum
    0.07
    ytt
    0.07
    ieder
    0.07
    afari
    0.07
    aldi
    0.07
    Activations Density 0.095%

    No Known Activations