© 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. 15-LLAMASCOPE-RES-131K
    11. 90179
    Prev
    Next
    INDEX
    Explanations

    monetary values and numerical identifiers related to financial transactions

    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
    виж
    -0.07
    彦
    -0.07
    voir
    -0.07
    iname
    -0.07
    ronic
    -0.07
    ViewById
    -0.06
    eniable
    -0.06
    bai
    -0.06
     вз
    -0.06
     иÑģ
    -0.06
    POSITIVE LOGITS
     Mills
    0.08
    raison
    0.06
    ÏĦια
    0.06
     Böl
    0.06
     Schro
    0.06
    ansa
    0.06
    gress
    0.06
     Ä°ngilizce
    0.06
    olds
    0.06
    Ä±ÅŁÄ±k
    0.05
    Activations Density 0.000%

    No Known Activations