© 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. 94251
    Prev
    Next
    INDEX
    Explanations

    numbers and their context in written form

    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
    aket
    -0.07
    ifton
    -0.07
    oard
    -0.07
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.07
    erdem
    -0.07
    dued
    -0.07
    hiba
    -0.07
    ÑĤаб
    -0.07
    pte
    -0.07
    ohon
    -0.07
    POSITIVE LOGITS
    ante
    0.08
    rops
    0.06
    ancel
    0.06
     robin
    0.06
     Barbar
    0.06
     Ñįлек
    0.06
    antes
    0.06
    Ñħи
    0.06
     Bright
    0.06
    ANTED
    0.06
    Activations Density 0.007%

    No Known Activations