© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    instances of the word "significant" and its variations

    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
    erman
    -0.07
    ãģĦãģĨ
    -0.07
    orman
    -0.07
    ucha
    -0.07
    .AutoScaleMode
    -0.07
    ject
    -0.07
    kir
    -0.07
    oq
    -0.06
    ÙĬس
    -0.06
    اÙĨÙĩ
    -0.06
    POSITIVE LOGITS
    ately
    0.10
    /sign
    0.09
    pants
    0.08
     amounts
    0.08
    amount
    0.08
     ölçüde
    0.08
    antly
    0.08
    ely
    0.08
    ively
    0.08
    reed
    0.07
    Activations Density 0.020%

    No Known Activations