© 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. 15-LLAMASCOPE-RES-131K
    11. 27257
    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
    ousel
    -0.08
    lix
    -0.08
    #ac
    -0.08
    าศ
    -0.07
    redo
    -0.07
    headline
    -0.07
    æľĭ
    -0.07
    actus
    -0.07
    zure
    -0.07
    allow
    -0.07
    POSITIVE LOGITS
    -force
    0.06
    opia
    0.06
     yapım
    0.06
    utta
    0.06
    ué
    0.06
     myself
    0.06
    UM
    0.05
    orce
    0.05
    570
    0.05
    pak
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.