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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 29429
    Prev
    Next
    INDEX
    Explanations

    questions and evaluations about worth, value, and legitimacy 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
     Raq
    -0.07
    çIJ´
    -0.06
     Cres
    -0.06
     Faction
    -0.06
    uzu
    -0.06
     hopefully
    -0.06
    åĩłä¸ª
    -0.06
     Corner
    -0.06
    inÄĽ
    -0.06
    estre
    -0.06
    POSITIVE LOGITS
     anymore
    0.12
     nor
    0.10
     ANY
    0.09
     anywhere
    0.08
     vůbec
    0.08
    nor
    0.08
    è¿Ļä¹Ī
    0.08
     unless
    0.07
    unless
    0.07
     вообÑīе
    0.07
    Activations Density 0.027%

    No Known Activations