© 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. 9-LLAMASCOPE-RES-131K
    11. 95264
    Prev
    Next
    INDEX
    Explanations

    elements related to navigation and directions

    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
     AssemblyCopyright
    -0.07
    ed
    -0.06
    apa
    -0.06
    é¡
    -0.06
    -API
    -0.06
    ibs
    -0.06
    ĶåĽŀ
    -0.06
    atur
    -0.06
    iana
    -0.06
    alama
    -0.06
    POSITIVE LOGITS
    128
    0.06
    ffi
    0.06
    assium
    0.06
     Sands
    0.06
     SUN
    0.06
    513
    0.06
     Relay
    0.06
     Vit
    0.06
    ritis
    0.06
     Sun
    0.06
    Activations Density 0.008%

    No Known Activations