© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 579
    Prev
    Next
    INDEX
    Explanations

    phrases related to abstract concepts and philosophical discussions

    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
    tul
    -0.08
     DevComponents
    -0.08
    _DIAG
    -0.08
    teg
    -0.07
    vette
    -0.07
    ÙĪاÙĦ
    -0.07
    iddet
    -0.07
     æľĿ
    -0.07
    idot
    -0.07
    IDD
    -0.07
    POSITIVE LOGITS
     tp
    0.06
    acock
    0.06
    .scalablytyped
    0.06
     Cousins
    0.06
    umo
    0.06
     TP
    0.06
    us
    0.06
    ¯ÃĤ
    0.06
     Umb
    0.06
    éĥ
    0.05
    Activations Density 0.000%

    No Known Activations