© 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. 15-LLAMASCOPE-RES-131K
    11. 192
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical representation and visualization of data

    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
     Rencontre
    -0.07
     jar
    -0.06
    257
    -0.06
    artic
    -0.06
     Scandin
    -0.06
    243
    -0.06
    590
    -0.06
    233
    -0.06
     Ñģебе
    -0.06
     ge
    -0.05
    POSITIVE LOGITS
    chin
    0.07
     trá»Ŀi
    0.06
    ály
    0.06
    pill
    0.06
    ckill
    0.06
    PRI
    0.06
    <<<
    0.06
    estro
    0.06
     Nug
    0.06
    inyin
    0.06
    Activations Density 0.043%

    No Known Activations