© 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. 96318
    Prev
    Next
    INDEX
    Explanations

    numeric or statistical references

    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
    dan
    -0.06
     вог
    -0.06
    oucher
    -0.06
    ÑĢеÑħ
    -0.06
    ستر
    -0.06
    bot
    -0.06
     neutral
    -0.06
    ierz
    -0.06
     neutr
    -0.05
     deficiency
    -0.05
    POSITIVE LOGITS
    amik
    0.07
    Ãłng
    0.07
    аÑĢÑħ
    0.07
    onaut
    0.07
    chaft
    0.07
    mî
    0.07
    CompatActivity
    0.07
    rames
    0.06
    rava
    0.06
    NOWLED
    0.06
    Activations Density 0.132%

    No Known Activations