© 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. 62125
    Prev
    Next
    INDEX
    Explanations

    numerical data and references within text, particularly related to publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    akens
    -0.06
    ziej
    -0.06
    InvalidOperationException
    -0.06
    681
    -0.06
    nar
    -0.06
     Kurulu
    -0.06
     append
    -0.06
    нен
    -0.06
    ientes
    -0.06
    positories
    -0.06
    POSITIVE LOGITS
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.06
     باÛĮ
    0.06
    vanished
    0.06
     Knight
    0.06
    .CLASS
    0.06
     McCorm
    0.06
    secondary
    0.06
     Rosen
    0.06
    .column
    0.06
    λÏİ
    0.06
    Activations Density 0.005%

    No Known Activations