© 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. 29343
    Prev
    Next
    INDEX
    Explanations

    multi-line formatted data or structured information commonly seen in programming or database contexts

    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
    ugin
    -0.07
    amber
    -0.07
    qus
    -0.07
    fdc
    -0.07
    ÑĤÑı
    -0.07
    renom
    -0.07
    oods
    -0.07
    Äįel
    -0.07
    .Site
    -0.07
    mere
    -0.07
    POSITIVE LOGITS
    iek
    0.06
    761
    0.06
    0.06
     mant
    0.05
     amongst
    0.05
    FORMANCE
    0.05
     Smart
    0.05
    .hamcrest
    0.05
    461
    0.05
    416
    0.05
    Activations Density 0.014%

    No Known Activations