© 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. 87917
    Prev
    Next
    INDEX
    Explanations

    elements with the 'inline' display property in CSS

    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
    //{{
    -0.10
    ropol
    -0.08
    berapa
    -0.08
    /compiler
    -0.08
    ÙĦÙĪد
    -0.08
    $MESS
    -0.08
    ><![
    -0.07
    lessly
    -0.07
    ethyst
    -0.07
    esis
    -0.07
    POSITIVE LOGITS
    -
    0.06
    worth
    0.06
    -flex
    0.06
     Favor
    0.05
    (
    0.05
     vers
    0.05
     favor
    0.05
    ISBN
    0.05
    mint
    0.05
    867
    0.05
    Activations Density 0.001%

    No Known Activations