© 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. 87233
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of reasons or justification

    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
     Brend
    -0.07
    ijd
    -0.07
    ral
    -0.07
    imet
    -0.06
    лоп
    -0.06
    orman
    -0.06
    aci
    -0.06
    举
    -0.06
    IFORM
    -0.06
    imat
    -0.06
    POSITIVE LOGITS
     because
    0.12
     obvious
    0.12
    because
    0.12
     reasons
    0.11
     Because
    0.10
     porque
    0.10
    Because
    0.10
     omdat
    0.10
    ecause
    0.09
    ï¼ĮåĽłä¸º
    0.09
    Activations Density 0.028%

    No Known Activations