© 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. 126126
    Prev
    Next
    INDEX
    Explanations

    references to challenges or obstacles

    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
    strap
    -0.07
    .dds
    -0.07
    lia
    -0.07
    èm
    -0.07
    ropa
    -0.07
    pearance
    -0.07
    aras
    -0.07
    lify
    -0.07
    ायन
    -0.07
    ear
    -0.07
    POSITIVE LOGITS
     khÄĥn
    0.10
    ly
    0.09
    iating
    0.09
    -to
    0.07
    -hard
    0.07
    xes
    0.07
    ERSHEY
    0.07
    mente
    0.06
    /question
    0.06
    ìĤ¬íķŃ
    0.06
    Activations Density 0.014%

    No Known Activations