© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125246
    Prev
    Next
    INDEX
    Explanations

    the concept of "itself" in various contexts

    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
    باز
    -0.06
    ond
    -0.06
    ware
    -0.06
    ville
    -0.06
    are
    -0.06
    _PROTO
    -0.06
     .
    -0.06
    fu
    -0.06
     snap
    -0.05
     zatÃŃmco
    -0.05
    POSITIVE LOGITS
     itself
    0.10
    maal
    0.09
    ï¸ı
    0.09
    -même
    0.09
    ì±Ħ
    0.08
    semblies
    0.07
    otope
    0.07
    -wsj
    0.07
    LOOR
    0.07
    ENCIL
    0.07
    Activations Density 0.012%

    No Known Activations