© 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. 92518
    Prev
    Next
    INDEX
    Explanations

    names of academic institutions or notable places

    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
    orum
    -0.08
    habi
    -0.07
    i
    -0.07
    istan
    -0.06
     DS
    -0.06
     Leer
    -0.06
    alla
    -0.06
    arness
    -0.06
    asses
    -0.06
     Wright
    -0.06
    POSITIVE LOGITS
    ghest
    0.08
    gart
    0.08
    archical
    0.08
    ighted
    0.08
    unday
    0.07
    SizeMode
    0.07
    dden
    0.07
    lacak
    0.07
    aldi
    0.07
    Ĺ
    0.07
    Activations Density 0.027%

    No Known Activations