© 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. 3915
    Prev
    Next
    INDEX
    Explanations

    terms related to increasing or escalating situations or trends

    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
     twice
    -0.07
    ampie
    -0.07
     Twice
    -0.06
    kus
    -0.06
    immel
    -0.06
     Pence
    -0.06
    ube
    -0.06
    utra
    -0.06
    enne
    -0.06
     immediately
    -0.06
    POSITIVE LOGITS
     increasingly
    0.19
    è¶Ĭ
    0.16
     Increasing
    0.12
     gradually
    0.11
     increasing
    0.11
     è¶
    0.11
    Increasing
    0.11
     steadily
    0.11
     slowly
    0.10
     lately
    0.10
    Activations Density 0.097%

    No Known Activations