Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44084
    Prev
    Next
    INDEX
    Explanations

    references to historical buildings or architecture

    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
    venida
    -0.08
    avou
    -0.07
    iloc
    -0.07
    å¿Ĩ
    -0.07
    adera
    -0.07
    irket
    -0.07
    urette
    -0.07
    avors
    -0.07
    ãĥ©ãĤ¯
    -0.07
     telefon
    -0.07
    POSITIVE LOGITS
     Tud
    0.10
     medieval
    0.10
     Medieval
    0.09
     surv
    0.09
     Flem
    0.08
     externally
    0.08
     Elizabeth
    0.08
     Early
    0.08
     Georgian
    0.08
     timber
    0.08
    Activations Density 0.005%

    No Known Activations