© 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. 40063
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to equations

    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
    ă
    -0.07
    he
    -0.06
    ould
    -0.06
    -0.06
     ob
    -0.06
     occ
    -0.05
    
    -0.05
    094
    -0.05
    ↵
    -0.05
    ad
    -0.05
    POSITIVE LOGITS
    .styleable
    0.08
    Wunused
    0.08
     KromÄĽ
    0.08
    Ñĵ
    0.08
    orrent
    0.08
     GOODMAN
    0.07
    Äįel
    0.07
    ecko
    0.07
    \Migrations
    0.07
    ůr
    0.07
    Activations Density 0.101%

    No Known Activations