© 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. 56284
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references related to industry and economic analysis

    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
    dur
    -0.07
    och
    -0.06
    ekte
    -0.06
    kode
    -0.06
     career
    -0.06
    ikes
    -0.06
    ikk
    -0.06
    çĬ¬
    -0.06
    nick
    -0.06
    itary
    -0.06
    POSITIVE LOGITS
    -transitional
    0.07
     lite
    0.07
    ï¸ı
    0.07
    agma
    0.07
     $č↵
    0.07
    alat
    0.06
    atz
    0.06
    ìĦ¸ìļĶ
    0.06
    á»ijn
    0.06
    senal
    0.06
    Activations Density 0.002%

    No Known Activations