© 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. 77054
    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
    engin
    -0.10
    nesc
    -0.07
    oogle
    -0.07
    retch
    -0.07
     simples
    -0.07
    artz
    -0.07
    èĤ¥
    -0.07
    ihil
    -0.07
    HASH
    -0.07
    sure
    -0.06
    POSITIVE LOGITS
    ávka
    0.07
    erson
    0.06
    /Runtime
    0.05
    æݪ
    0.05
    753
    0.05
     âĵĺ
    0.05
    aka
    0.05
    ana
    0.05
    caled
    0.05
     Michaels
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.