© 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. 28936
    Prev
    Next
    INDEX
    Explanations

    data structures and programming constructs in code snippets

    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
    arp
    -0.07
    chip
    -0.07
    @mail
    -0.07
    rets
    -0.06
    phin
    -0.06
    oles
    -0.06
    hurst
    -0.06
     Steven
    -0.06
    steen
    -0.06
     Chip
    -0.06
    POSITIVE LOGITS
    shire
    0.07
    aida
    0.07
    .asc
    0.06
     vidé
    0.06
    инÑĥв
    0.06
    Įĵ
    0.06
     subsidi
    0.06
    alÄ±ÅŁ
    0.06
    nah
    0.06
    ders
    0.06
    Activations Density 0.004%

    No Known Activations