© 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. 3445
    Prev
    Next
    INDEX
    Explanations

    metadata related to digital content

    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
    bedo
    -0.06
     Giov
    -0.06
    andi
    -0.06
     awakeFromNib
    -0.06
     Definition
    -0.06
     Buck
    -0.06
     Mir
    -0.05
    =cut
    -0.05
    nier
    -0.05
    ihan
    -0.05
    POSITIVE LOGITS
    adr
    0.07
    vise
    0.07
    polator
    0.07
    ãĤ·ãĥ£ãĥ«
    0.07
    .blog
    0.07
    .trip
    0.07
     lục
    0.07
    abase
    0.07
    اÙĩد
    0.07
    raphics
    0.07
    Activations Density 0.002%

    No Known Activations