© 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. 17-LLAMASCOPE-RES-131K
    11. 39379
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Diego" or variations of it

    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
    rnek
    -0.08
    wig
    -0.08
    chte
    -0.07
     Mouth
    -0.07
    lÃŃn
    -0.07
     BindingFlags
    -0.07
    nder
    -0.07
    éĺħ读次æķ°
    -0.07
    ning
    -0.07
    xbb
    -0.07
    POSITIVE LOGITS
    lectric
    0.09
    longleftrightarrow
    0.07
     abstract
    0.07
    ÅĤo
    0.06
    omal
    0.06
    hard
    0.06
     Dun
    0.06
    ait
    0.06
    ilename
    0.06
    ÑĢеÑģÑģ
    0.06
    Activations Density 0.002%

    No Known Activations