© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    terms related to foam and spongy materials

    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
    aque
    -0.07
    añ
    -0.07
    ações
    -0.07
    a
    -0.07
    hook
    -0.07
    å¥Ī
    -0.06
    asca
    -0.06
     hook
    -0.06
    i
    -0.06
    atas
    -0.06
    POSITIVE LOGITS
    ery
    0.10
    ikel
    0.09
    ERY
    0.08
    iness
    0.07
    imals
    0.07
    ró
    0.07
    iero
    0.07
    ede
    0.07
    ãĥĨãĥ«
    0.07
    posite
    0.07
    Activations Density 0.004%

    No Known Activations