© 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. 17-LLAMASCOPE-RES-131K
    11. 86784
    Prev
    Next
    INDEX
    Explanations

    statements regarding website security and compatibility

    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
    ALSE
    -0.08
    oire
    -0.08
    reck
    -0.07
    erable
    -0.07
    viÄį
    -0.07
    atables
    -0.07
    651
    -0.06
    arrass
    -0.06
    reat
    -0.06
    afka
    -0.06
    POSITIVE LOGITS
    erna
    0.07
    jam
    0.06
    icz
    0.06
    ota
    0.06
    das
    0.06
     Yue
    0.06
    IC
    0.06
     Cater
    0.06
     virus
    0.06
    igan
    0.06
    Activations Density 0.001%

    No Known Activations