© 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. 56825
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to demographics and accommodations

    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
    htm
    -0.07
    esian
    -0.06
    ief
    -0.06
     such
    -0.06
    udio
    -0.06
    âĨ
    -0.06
     now
    -0.06
    wie
    -0.06
    Reviewed
    -0.05
    ÑĢави
    -0.05
    POSITIVE LOGITS
    Legend
    0.09
    ogle
    0.08
    ILLE
    0.08
    _Tis
    0.07
    CrLf
    0.07
    åIJĦ
    0.07
    ëıĦë³Ħ
    0.07
     åIJĦ
    0.07
     pek
    0.07
    idal
    0.07
    Activations Density 0.026%

    No Known Activations