© 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. 78315
    Prev
    Next
    INDEX
    Explanations

    references to philosophical concepts and their relationships within various disciplines

    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
     Dexter
    -0.06
     insert
    -0.06
    intel
    -0.06
     Drew
    -0.06
     inserts
    -0.06
    icult
    -0.05
    illet
    -0.05
    aine
    -0.05
     desp
    -0.05
    جÙĦ
    -0.05
    POSITIVE LOGITS
     Misc
    0.09
    .scalablytyped
    0.08
    apus
    0.07
    à¹Īวà¸ĩ
    0.07
    unifu
    0.07
    lán
    0.07
    äng
    0.07
    gesch
    0.06
    /misc
    0.06
    OTOS
    0.06
    Activations Density 0.013%

    No Known Activations