© 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. 93884
    Prev
    Next
    INDEX
    Explanations

    specific technical specifications related to memory and storage capacity in devices

    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
    hood
    -0.07
    witch
    -0.07
    .BigInteger
    -0.07
    icularly
    -0.06
    hoff
    -0.06
    977
    -0.06
    760
    -0.06
    .rd
    -0.06
     conquer
    -0.06
    hores
    -0.06
    POSITIVE LOGITS
    AGE
    0.07
    nop
    0.07
    ForKey
    0.07
     dak
    0.06
    blings
    0.06
    imos
    0.06
    ulin
    0.06
    ìĬ¤íħĮ
    0.06
    dma
    0.06
    zing
    0.06
    Activations Density 0.004%

    No Known Activations