© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29716
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and metadata in a document

    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
    rix
    -0.06
    -st
    -0.06
    ocio
    -0.06
     Secrets
    -0.06
     Solic
    -0.06
     coll
    -0.05
    zell
    -0.05
    olic
    -0.05
    oli
    -0.05
    bed
    -0.05
    POSITIVE LOGITS
    icontrol
    0.08
    äch
    0.08
    anio
    0.07
     داش
    0.07
    POCH
    0.07
    :eq
    0.07
     chÃŃ
    0.07
    .rel
    0.07
    ĮĴ
    0.07
    ENDOR
    0.07
    Activations Density 0.002%

    No Known Activations