© 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. 5-LLAMASCOPE-RES-131K
    11. 125963
    Prev
    Next
    INDEX
    Explanations

    terms related to fine arts and artistic disciplines

    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
    оÑĢод
    -0.07
    engin
    -0.07
    âĶģ
    -0.07
    StateException
    -0.07
    .arraycopy
    -0.06
     ActionController
    -0.06
    егоÑĢ
    -0.06
    å°¿
    -0.06
    пов
    -0.06
    ạng
    -0.06
    POSITIVE LOGITS
     Suns
    0.07
     CHR
    0.06
     Chris
    0.06
    boo
    0.06
    gm
    0.06
    ummings
    0.06
    bish
    0.06
    rea
    0.06
    post
    0.05
    akis
    0.05
    Activations Density 0.044%

    No Known Activations