© 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. 119070
    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
    .idea
    -0.07
     Onion
    -0.06
    Ñģком
    -0.06
    lesi
    -0.06
     Norris
    -0.06
     inkl
    -0.06
    esin
    -0.06
     resourceName
    -0.06
    ierge
    -0.06
    .createFrom
    -0.06
    POSITIVE LOGITS
    ãģĸ
    0.07
    ÅĻÃŃd
    0.06
    '])){
    0.06
    uma
    0.06
    对æĸ¹
    0.06
     Maj
    0.06
     Fritz
    0.06
     precisely
    0.06
    "url
    0.06
     Resume
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.