© 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. 126943
    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
    appa
    -0.08
    ElementException
    -0.08
    anuts
    -0.08
    êu
    -0.07
    кÑĢеÑĤ
    -0.07
    orias
    -0.07
    roj
    -0.07
    dden
    -0.07
    ylon
    -0.07
    	TokenName
    -0.07
    POSITIVE LOGITS
     Dag
    0.07
     Gust
    0.06
     Figure
    0.06
     Cat
    0.06
    Figure
    0.06
     M
    0.06
     detail
    0.06
     Tale
    0.05
     Savage
    0.05
     x
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.