Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5694
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and mapping languages

    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
    ะ
    -0.07
    ouro
    -0.07
     hâl
    -0.06
    CU
    -0.06
    pcm
    -0.06
    trieve
    -0.06
    lio
    -0.06
    tro
    -0.06
    EDIA
    -0.06
    .apple
    -0.06
    POSITIVE LOGITS
     Qgs
    0.11
     iface
    0.09
     raster
    0.08
    Raster
    0.08
    layer
    0.08
     Spatial
    0.07
    layers
    0.07
     spatial
    0.07
     layers
    0.07
    .spatial
    0.07
    Activations Density 0.002%

    No Known Activations