© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98075
    Prev
    Next
    INDEX
    Explanations

    references to anonymity or anonymous identities

    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
    éc
    -0.08
    umo
    -0.07
    pb
    -0.07
     Glas
    -0.07
    ãĥĪãĥª
    -0.07
    elay
    -0.07
    oyo
    -0.07
    åĩ
    -0.07
    oS
    -0.07
    ãĥªãĤ¹
    -0.07
    POSITIVE LOGITS
     silence
    0.06
    awe
    0.06
    plier
    0.06
     Farr
    0.06
     quant
    0.06
    /sec
    0.06
     ding
    0.06
    704
    0.06
     conj
    0.05
    ponse
    0.05
    Activations Density 0.001%

    No Known Activations