© 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. 82992
    Prev
    Next
    INDEX
    Explanations

    references to military units and organizations

    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
    aliz
    -0.06
    onian
    -0.06
    à¥įण
    -0.06
    arious
    -0.06
    esel
    -0.06
    atical
    -0.06
    byn
    -0.06
    olv
    -0.06
    /her
    -0.06
    ÃŁen
    -0.06
    POSITIVE LOGITS
    let
    0.08
    _locs
    0.07
    ãĥ¼ãĥĨãĤ£
    0.07
    ClientRect
    0.07
    sembl
    0.06
    igure
    0.06
    _TypeDef
    0.06
     Ferguson
    0.06
    æļ
    0.06
    atics
    0.06
    Activations Density 0.060%

    No Known Activations