© 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. 61610
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific entities mentioned in the text

    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
    wers
    -0.07
    .builders
    -0.07
    ãģ®æĸ¹
    -0.07
    aal
    -0.07
    ÃĸL
    -0.07
     seedu
    -0.07
    oje
    -0.06
     hilar
    -0.06
    nze
    -0.06
    isy
    -0.06
    POSITIVE LOGITS
    Calibri
    0.07
    Verdana
    0.07
    ses
    0.07
    ship
    0.06
     beat
    0.06
    sp
    0.06
    acher
    0.06
     Beat
    0.05
     pun
    0.05
     entail
    0.05
    Activations Density 0.028%

    No Known Activations