© 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. 16237
    Prev
    Next
    INDEX
    Explanations

    sequences of alphanumeric characters, especially focusing on their casing and specific symbols

    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
    stry
    -0.08
    uzey
    -0.07
    lemn
    -0.07
    abo
    -0.07
    ogan
    -0.07
    och
    -0.07
    emaker
    -0.07
    isp
    -0.07
    fect
    -0.07
     обол
    -0.07
    POSITIVE LOGITS
    kest
    0.06
     Baron
    0.06
    OnInit
    0.06
    AccessType
    0.06
    erver
    0.06
    izedName
    0.06
    ValueCollection
    0.06
    دÛĮگر
    0.06
    inded
    0.06
    antas
    0.06
    Activations Density 0.002%

    No Known Activations