© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1355
    Prev
    Next
    INDEX
    Explanations

    quantitative or numerical data

    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
    -t
    -0.06
    3
    -0.06
    uc
    -0.06
    rypton
    -0.06
    yah
    -0.06
    ta
    -0.05
    ylon
    -0.05
    -f
    -0.05
     blessing
    -0.05
     Essay
    -0.05
    POSITIVE LOGITS
    ennen
    0.08
    £i
    0.08
    -marker
    0.07
    NavController
    0.07
     Eag
    0.07
    .openapi
    0.07
    NCY
    0.07
    ousel
    0.07
    ãĤ¤ãĤ¯
    0.07
    itos
    0.07
    Activations Density 0.082%

    No Known Activations