© 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. 56257
    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
    uw
    -0.06
    ossa
    -0.06
     brainstorm
    -0.06
     grass
    -0.06
     consumer
    -0.06
    &s
    -0.05
     impress
    -0.05
     bro
    -0.05
     geri
    -0.05
     rop
    -0.05
    POSITIVE LOGITS
    ertas
    0.08
     noreferrer
    0.08
     performan
    0.07
    amus
    0.07
    ildo
    0.07
    feeds
    0.07
    achable
    0.07
    erras
    0.07
    cano
    0.07
    ertest
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.